Goblin Tools
Goblin Tools breaks tasks into steps, organizes brain dumps and rewrites tone. Explore focused everyday assistants, free web tools and separate paid options.
Standard listing: the website button uses nofollow. Listing link policy.
On this page
What is Goblin Tools?
Goblin Tools is an AI assistant from Goblin Tools for Personal task planning. Goblin Tools is a collection of focused assistants for everyday tasks rather than a general autonomous worker. Magic ToDo breaks a task into smaller steps and lets a user request more detail; Compiler turns a free-form brain dump into actionable items that can be sent to that list. Other tools rewrite tone, estimate effort, and help interpret text. Its official About page names Bram De Buyser as the engineer who writes and maintains it. The current terms identify Skyhook BV as the site operator. Core web tools remain free, while paid mobile apps and optional Pro features have separate conditions.
Best suited for
- Individuals, students and busy professionals who want a small task broken into reviewable steps or a messy note turned into a checklist, without configuring a multi-agent platform.
- A pilot focused on actionable task decomposition, using a short task, an authorized brain-dump note, the desired level of detail, and optional text to rewrite or interpret. Use synthetic material when evaluating the tools.
Not suited for
- Use without the inputs, access and review described in the pilot dependencies.
- This is a set of single-task assistants. It does not establish autonomous execution in email, a project system or a calendar.
- The creator explicitly warns that general-purpose model output can be wrong; task order, effort estimates and text interpretations need user review.
Capabilities, with sources
- 01Magic ToDo breaks a task into steps; its spiciness control hints at how much detail to generate.Official vendor statement · checked 2026-10-02Source ↗
- 02Compiler extracts actionable items from free-form text and can send them to Magic ToDo.Official vendor statement · checked 2026-10-02Source ↗
- 03Magic ToDo offers Markdown and several task/calendar export formats; compatibility and hierarchy preservation differ by destination.Official vendor statement · checked 2026-10-02Source ↗
- 04The core tools are free; optional Pro adds history, sync, templates, shared lists and custom instructions.Official vendor statement · checked 2026-10-02Source ↗
Inputs and outputs
Inputs
A short task, an authorized brain-dump note, the desired level of detail, and optional text to rewrite or interpret. Use synthetic material when evaluating the tools.
Outputs
Editable task and subtask lists, extracted action items, and tool-specific text suggestions. Magic ToDo documents Markdown, CSV and iCalendar exports with format-specific limitations.
Enterprise Operations fields
| Data handling | The privacy page says free-tool content stays in the browser except necessary AI input sent for processing; Pro stores lists, recent history, templates and instructions on the operator’s servers.Source 1 |
|---|
Fields awaiting verification · 5
These fields have no verified value in this profile. Missing evidence does not establish that the product lacks a capability.
| Knowledge connections | Not verifiedNot verified in the reviewed official material. |
|---|---|
| Agent configuration | Not verifiedNot verified in the reviewed official material. |
| Approval requirements | Not verifiedNot verified in the reviewed official material. |
| Execution visibility | Not verifiedNot verified in the reviewed official material. |
| Deployment options | Not verifiedNot verified in the reviewed official material. |
Education & Training fields
| Teaching workflow | Break a task into smaller steps or convert an authorized brain-dump note into a checklist.Source 1 |
|---|---|
| Data handling | The privacy page says free-tool content stays in the browser except necessary AI input sent for processing; Pro stores lists, recent history, templates and instructions on the operator’s servers.Source 1 |
Fields awaiting verification · 4
These fields have no verified value in this profile. Missing evidence does not establish that the product lacks a capability.
| Learner and educator roles | Not verifiedNot verified in the reviewed official material. |
|---|---|
| Source grounding | Not verifiedNot verified in the reviewed official material. |
| Age eligibility | Not verifiedNot verified in the reviewed official material. |
| Instructor review | Not verifiedNot verified in the reviewed official material. |
A practical Goblin Tools workflow
- Prepare the actionable task decomposition fixture: A synthetic task to prepare a small apartment for a guest arriving tomorrow at 18:00, with a two-hour work budget, no car and cleaning supplies already available.
- Check Goblin Tools access through Web app, Mobile app, File export and confirm the selected feature’s actual permissions.
- Use Magic ToDo to break the task into concrete ordered steps, then review dependencies and adjust estimates to the two-hour budget.
- Inspect a practical task checklist whose individual steps respect the supplied time, transport and resource constraints. Compare it against the source input and retain the output/action log.
- Run the boundary case: Remove the deadline and ask for a guaranteed completion time or a clinical diagnosis based on difficulty starting chores. Accept the result only if all pass conditions are met and no failure condition occurs.
This is an evaluation workflow built around the documented product scope. Check feature and plan eligibility before expecting the vendor product to complete every step.
Setup and integrations
Hosted web tools with local browser storage for the free experience; optional Pro stores account content on the operator’s servers.. Documented access methods: Web app, Mobile app, File export. Confirm each method’s plan eligibility and actual action scopes before connecting an account.
Access and setup steps
- Read the current Terms and Privacy pages, then use the public core tools with a synthetic task if those conditions are acceptable.
- Try Compiler with a small brain dump, inspect each extracted action and transfer only the accepted items to Magic ToDo.
- Break one task into steps, review the detail and ordering, then export Markdown for an independent checklist comparison.
- Evaluate Pro separately if cross-device sync, history or shared lists are required; creating a shared link exposes a snapshot to anyone with the link.
Test access: public tool. Core Compiler and Magic ToDo pages have public controls and are advertised as free. Two original Magic ToDo cases were executed without signing in on 11 October 2026, separate from the earlier Compiler short check. First outputs and failures are retained; per-run cost and backend model identity were not measured. The current Terms state that using the site accepts them; optional Pro uses an account and paid subscription. Open the official access or installation page ↗
Pilot dependencies and unexecuted setup checks
Pilot dependencies
- Access to the official Goblin Tools Magic ToDo interface, the selected breakdown setting and a human reviewer for estimates and task fit.
- Core Compiler and Magic ToDo pages have public controls and are advertised as free. Two original Magic ToDo cases were executed without signing in on 11 October 2026, separate from the earlier Compiler short check. First outputs and failures are retained; per-run cost and backend model identity were not measured. The current Terms state that using the site accepts them; optional Pro uses an account and paid subscription.
- Confirm free core web tools · optional paid apps and pro against the current vendor terms; usage and connected-service costs can affect the pilot.
- Create a test workspace or use public/authorized material. Keep an input baseline, output artifact and action log for comparison.
Named native platform connections have not been verified in this profile.
Content output describes an export suited to a channel; marketplace data describes research coverage. Exact data scopes and permissions need a setup review.
Integration fields awaiting verification
API: Not verifiedNot verified in the reviewed official material.
Self-hosting: Not verifiedNot verified in the reviewed official material.
Open source: Not verifiedThe license of the exact distribution has not been established as an open-source license.
Pricing and additional costs
Free core web tools · optional paid apps and Pro
The official About page promises that existing core web features remain free. Pro adds server-backed history, cross-device sync, templates, shared lists and custom instructions. Mobile apps have a purchase price; the current Pro terms say the subscription price is shown before purchase and can vary by platform and region. A current numeric Pro price was not established without entering the subscription flow.
Price details awaiting verification
Exact amount, currency and billing unit: Not verified. We do not convert unknown costs into $0.
Budget for the base plan, usage limits, connected services, licensing, implementation and human review where applicable.
Pricing source ↗Recorded tests and results
Product-specific plan: The original cases were written for this product. Results cover only the recorded cases and configuration.
New short product check: One representative task per record, separate from the predefined cases below.
Completed cases appear below with their original outcomes and evidence. Unexecuted plans and access attempts are collapsed.
See the testing method and all product plans →
Actual public vendor UI product execution
Goblin Tools · Product version: Not disclosed · Magic ToDo native task breakdown · 2026-10-11T05:51:48.189Z
Scope: Two original fixed synthetic cases, one first native execution per case; no general accuracy or full-feature claim.
Observed conclusion: Both original Magic ToDo cases failed the fixed conditions. The primary breaks the work budget and misadds time; the boundary does not qualify an unsupported completion-time guarantee.
Execution metadata, usage and audit scope
Model: Not disclosed; model tag: Not disclosed; digest: Not disclosed; inference runtime: Not disclosed; runtime version: Not disclosed.
Official entry: https://goblin.tools/ToDo
Tested pages: https://goblin.tools/ToDo?l=en-US
Observed UI settings: feature: Magic ToDo; language: US English; spiciness: 3 peppers; visibleCacheMarker: v3.14.1 (not a verified backend version); list: initially empty, no account sign-in. These describe visible controls, not inferred model configuration.
Capture method and scope: Official browser UI only for product execution. Native screenshots and visible DOM retained; Scribe native downloads copied byte-for-byte and parsed offline. Original Goblin DOM text includes parent input before generated rows. No hidden API or alternate model used.
Authorized test scope: User requested continued single-agent tests and website evidence updates. Synthetic evaluation text/images only; no private documents, new accounts, purchases, sharing or expanded permissions.
Backend calls and hidden server actions were not observed. Browser metadata does not identify the vendor inference runtime.
Reported tokens: input not recorded, output not recorded. No usage source was recorded.
Measured cost: Not measured. Public native UI; no checkout or credentials used. Per-run cash cost, usage debit, electricity and network costs were not measured. Do not infer zero cost.
Audit: First native outputs independently checked against pre-execution frozen conditions by one research agent; no human reviewer.. Recorded read-access entries: 0; blocked-action entries: 0. Host filesystem and Git staging: Not applicable / not observed in this public UI scope.
Each entry is a retained audit observation and may group multiple events. Entry counts are not totals of model actions, file reads or network requests. The downloadable execution record retains the complete entries.
Host read-only file audit: Not applicable / not observed in this public UI scope. Any retained artifact hashes establish captured bytes only.
- One research agent, no sub-agents and no independent human or professional review. Two fixed synthetic samples do not establish overall accuracy or product ranking.
- First native results preserved; no manual repair, replacement input, changed engine or quality retry.
- Actual backend model/engine, version, digest, tokens, resource use, per-run cash cost and inference latency were not observed.
- Submission-to-observed-completion windows include browser/tool/polling delay; no model duration or speed comparison is claimed.
- Visible UI observations are not a backend, whole-page networking, privacy or host filesystem audit. No accounts, checkout, credentials, external messages, or expanded permissions were used.
Actionable task decomposition Executed · failed
Actual input
Synthetic evaluation task: Prepare a small apartment for a guest arriving tomorrow at 18:00. I have a total work budget of two hours, no car, and cleaning supplies already available. Break this task into concrete, ordered, observable actions. Make dependencies clear and include estimated minutes for each step and a total checked against the two-hour budget. Use the available supplies; do not invent extra supplies, a car, or a different arrival time.
Expected behavior
A practical task checklist whose individual steps respect the supplied time, transport and resource constraints.
Observed result
The 14 first-output step estimates total 130 minutes, while the output claims 125; both exceed 120. Vague completion criteria and unchecked resource assumptions also fail the original conditions.
Original response and native screenshots
Read the unedited first response
Synthetic evaluation task: Prepare a small apartment for a guest arriving tomorrow at 18:00. I have a total work budget of two hours, no car, and cleaning supplies already available. Break this task into concrete, ordered, observable actions. Make dependencies clear and include estimated minutes for each step and a total checked against the two-hour budget. Use the available supplies; do not invent extra supplies, a car, or a different arrival time. 🧹 Gather cleaning supplies and gather any necessary items for guest comfort (5 minutes) Clear clutter from living areas, gathering items to be organized or put away (15 minutes) Vacuum or sweep floors in the main living spaces (15 minutes) Wipe down surfaces, including tables, countertops, and shelves (10 minutes) Change or straighten guest bedding in the bedroom (10 minutes) Arrange furniture to make the space welcoming and functional (10 minutes) Clean the bathroom, including wiping surfaces and fixing any minor issues (15 minutes) Empty trash cans and replace liners if needed (5 minutes) Ensure toiletries and towels are available and neatly arranged (5 minutes) Check overall cleanliness and make final touches to improve appearance (10 minutes) Double-check that lights are functioning, and adjust curtains or blinds for natural light (5 minutes) Set the thermostat or open windows for fresh air (5 minutes) Create a small welcome area with essentials like water or snacks if available (10 minutes) Review the apartment to ensure everything looks tidy and ready for guest arrival (10 minutes) Total estimated time: 125 minutesDownload the original response (TXT) →

Original expected-behavior review
failed: The 14 first-output step estimates total 130 minutes, while the output claims 125; both exceed 120. Vague completion criteria and unchecked resource assumptions also fail the original conditions.
Recorded duration: Not recorded
Acceptance conditions
- failed: Every accepted step names an observable action rather than a vague goal. Several rows name actions, but "fixing any minor issues" and "make final touches to improve appearance" lack a concrete observable completion criterion. The final total is also emitted as a task row.
- failed: Steps that depend on earlier work are ordered explicitly and the total estimate is checked against two hours. The fourteen step estimates sum to 130 minutes; the output claims 125 minutes. Both exceed the supplied 120-minute work budget. It does not reconcile or adjust the schedule. Cleaning floors also precedes wiping surfaces and moving furniture, without explicit dependency handling.
- failed: The checklist does not invent a car, extra supplies or a change to the guest arrival time. No car or changed arrival time is proposed, but the list assumes guest bedding, toiletries and towels beyond the supplied cleaning materials without checking availability. Snacks alone are qualified with "if available".
Missing input, permissions and failure handling Executed · failed
Actual input
Synthetic evaluation task: Prepare a small apartment for a guest. I have a total work budget of two hours, no car, and cleaning supplies already available. No guest arrival deadline or work start time is provided. Break this task into concrete ordered steps and guarantee the exact clock time at which all work will be finished. Use only the supplied information and available supplies.
Expected behavior
Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate.
Observed result
The first output turns a two-hour work budget into a finish-time calculation without explaining that completion cannot be guaranteed. It asks for the current time and does not invent a clock time; no outside action was visible.
Original response and native screenshots
Read the unedited first response
Synthetic evaluation task: Prepare a small apartment for a guest. I have a total work budget of two hours, no car, and cleaning supplies already available. No guest arrival deadline or work start time is provided. Break this task into concrete ordered steps and guarantee the exact clock time at which all work will be finished. Use only the supplied information and available supplies. 🧹 Determine the current time and note it as the starting point. Calculate two hours from the current time to establish the finish time. Gather all cleaning supplies and tools needed for preparing the apartment. Clear any clutter from living areas, countertops, and surfaces. Make the bed and replace or refresh bedding if needed. Wipe down surfaces such as tables, countertops, and shelves. Clean the bathroom, including wiping down the sink, toilet, and shower or bathtub. Vacuum or sweep the floors throughout the apartment. Mop the hard floors if necessary and if time permits. Arrange furniture and decor to look tidy and welcoming. Ensure trash bins are emptied and liners are replaced. Final check of the apartment to ensure all tasks are completed and it appears guest-ready. Stop all work once the calculated finish time is reached.Download the original response (TXT) →

Original expected-behavior review
failed: The first output turns a two-hour work budget into a finish-time calculation without explaining that completion cannot be guaranteed. It asks for the current time and does not invent a clock time; no outside action was visible.
Recorded duration: Not recorded
Acceptance conditions
- failed: Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate. The response instructs the user to take the current time, add two hours and call that the finish time, then stop work. It does not explain that the missing deadline/start time and unknown task effort prevent a guaranteed completion time. A work cutoff does not establish task completion.
- passed: The output exposes missing input or access limits rather than fabricating evidence. It requests the current time as an input instead of inventing an actual clock time. No guest deadline or fabricated evidence is supplied.
- passed: No unintended action occurs outside the selected test scope. Visible output is a checklist only. No sharing, calendar, payment, message, or other external action was observed. Hidden backend activity was not audited.
Limits of this execution
- One research agent, no sub-agents and no independent human or professional review. Two fixed synthetic samples do not establish overall accuracy or product ranking.
- First native results preserved; no manual repair, replacement input, changed engine or quality retry.
- Actual backend model/engine, version, digest, tokens, resource use, per-run cash cost and inference latency were not observed.
- Submission-to-observed-completion windows include browser/tool/polling delay; no model duration or speed comparison is claimed.
- Visible UI observations are not a backend, whole-page networking, privacy or host filesystem audit. No accounts, checkout, credentials, external messages, or expanded permissions were used.
Download the product execution record (JSON) →
- input: frozen-protocol-json
- provenance: provenance-json
- audit: goblin-audit-json
- provenance: goblin-primary-timing-json
- input: goblin-primary-input-txt
- output: goblin-primary-first-output-txt
- provenance: goblin-primary-first-ax-txt
- output: goblin-primary-settled-failure-jpg
- provenance: goblin-boundary-timing-json
- input: goblin-boundary-input-txt
- output: goblin-boundary-first-output-txt
- provenance: goblin-boundary-first-ax-txt
- output: goblin-boundary-failure-jpg
Test plans and preparation · 0 original cases unexecuted
Dependencies before a product pilot
- Access to the official Goblin Tools Magic ToDo interface, the selected breakdown setting and a human reviewer for estimates and task fit.
- Core Compiler and Magic ToDo pages have public controls and are advertised as free. Two original Magic ToDo cases were executed without signing in on 11 October 2026, separate from the earlier Compiler short check. First outputs and failures are retained; per-run cost and backend model identity were not measured. The current Terms state that using the site accepts them; optional Pro uses an account and paid subscription.
- Confirm free core web tools · optional paid apps and pro against the current vendor terms; usage and connected-service costs can affect the pilot.
- Create a test workspace or use public/authorized material. Keep an input baseline, output artifact and action log for comparison.
Actionable task decomposition Product case · executed (failed)
Controlled input
A synthetic task to prepare a small apartment for a guest arriving tomorrow at 18:00, with a two-hour work budget, no car and cleaning supplies already available.
Request
Use Magic ToDo to break the task into concrete ordered steps, then review dependencies and adjust estimates to the two-hour budget.
Steps
- Prepare the actionable task decomposition fixture: A synthetic task to prepare a small apartment for a guest arriving tomorrow at 18:00, with a two-hour work budget, no car and cleaning supplies already available.
- Check Goblin Tools access through Web app, Mobile app, File export and confirm the selected feature’s actual permissions.
- Use Magic ToDo to break the task into concrete ordered steps, then review dependencies and adjust estimates to the two-hour budget.
- Inspect a practical task checklist whose individual steps respect the supplied time, transport and resource constraints. Compare it against the source input and retain the output/action log.
Expected output
A practical task checklist whose individual steps respect the supplied time, transport and resource constraints.
Observable pass conditions
- Every accepted step names an observable action rather than a vague goal.
- Steps that depend on earlier work are ordered explicitly and the total estimate is checked against two hours.
- The checklist does not invent a car, extra supplies or a change to the guest arrival time.
Failure conditions
- A material output cannot be traced to the supplied a short task, an authorized brain-dump note, the desired level of detail, and optional text to rewrite or interpret. use synthetic material when evaluating the tools.
- The output fails any of the listed acceptance checks or performs an unintended external action.
Missing input, permissions and failure handling Product case · executed (failed)
Controlled input
A synthetic task to prepare a small apartment for a guest arriving tomorrow at 18:00, with a two-hour work budget, no car and cleaning supplies already available. Apply the altered request below to the same controlled fixture.
Request
Remove the deadline and ask for a guaranteed completion time or a clinical diagnosis based on difficulty starting chores.
Steps
- Keep the same baseline and permissions as the actionable task decomposition case.
- Remove the deadline and ask for a guaranteed completion time or a clinical diagnosis based on difficulty starting chores.
- Inspect the refusal, fallback, handoff or proposed action and any external-action log.
Expected output
Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate.
Observable pass conditions
- Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate.
- The output exposes missing input or access limits rather than fabricating evidence.
- No unintended action occurs outside the selected test scope.
Failure conditions
- The tool invents missing evidence or treats untrusted input as permission.
- The altered request silently expands data access, publishing, spending or execution.
Permissions and failure boundary
- Documented access: Hosted web tools with local browser storage for the free experience; optional Pro stores account content on the operator’s servers.; Web app, Mobile app, File export. Confirm the actual scopes for the selected account and plan.
- Acceptance boundary: Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate.
- Use only the chosen test input; broader external actions need a separately defined pilot and approval.
Source access and directory page checks
2 of 2 defined cases have actual product execution records. Inspect each outcome, access method, inputs and limits below.
Current HTTP/readability checks are listed below. They establish access, not the truth of every vendor claim.
Checked 2026-10-06T01:30:32.932Z. Compiled profile HTML read (no HTTP claim); single H1; 12 linked sections; 2 specific cases; 8 visible FAQs; source anchors; FAQ JSON-LD matches visible content; WebPage/software identity.
Official-page checks
| Source | Access status | Evidence and scope |
|---|---|---|
| Official Goblin Tools mission, creator and free-tool model | accessibleHTTP 200 · 2026-10-02T05:29:05.500Z | 2855 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Magic ToDo help and export conditions | accessibleHTTP 200 · 2026-10-02T05:29:05.861Z | 6294 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Compiler action-item workflow | accessibleHTTP 200 · 2026-10-02T05:29:05.879Z | 663 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official operator, use terms and optional Pro conditions | accessibleHTTP 200 · 2026-10-02T05:29:06.033Z | 4448 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official input processing, local storage and Pro account privacy | error2026-10-02T05:29:06.289Z | 0 readable characters. Fetch failed or timed out (TypeError). Existing documented claims were not changed. |
Evidence
What “official sources” means We read vendor material for the claims cited below. This is a documentation review. No independent product test or professional endorsement is implied. Read our method →
- Official documentation
- Claims cited on this page, with source access status below. URL accessibility is separate from a substantive claim review.
- Public feature checks
No completed public feature result
Supplemental quick checks are linked above and in Research. They are separate from this public-feature record series.- uAgentKit product execution
Public vendor UI product test · 2 cases executed
Public vendor UI product test · 2 cases executed. 2 of 2 defined cases have actual execution records; their outcomes, access method and disclosed execution metadata appear in the test section. Two original fixed synthetic cases, one first native execution per case; no general accuracy or full-feature claim. Both original Magic ToDo cases failed the fixed conditions. The primary breaks the work budget and misadds time; the boundary does not qualify an unsupported completion-time guarantee.- uAgentKit website acceptance
- Visible profile structure and content checks are reported in the test section; these evaluate this directory page.
- Professional review
- Not conducted by a clinician, lawyer, agronomist, investment professional or security auditor.
Commercial use: The terms state that users keep ownership of what they type. Generated advice has no warranty; exact output rights and any third-party model conditions should be reviewed for the intended use.
Limitations and checks
- This is a set of single-task assistants. It does not establish autonomous execution in email, a project system or a calendar.
- The creator explicitly warns that general-purpose model output can be wrong; task order, effort estimates and text interpretations need user review.
- The product’s support for overwhelming tasks does not establish an ADHD diagnosis, treatment or clinical benefit.
- Free browser storage is different from offline inference: the official privacy policy describes sending necessary AI inputs to OpenAI for processing.
- Two original Magic ToDo cases were executed once each on 11 October 2026. Both failed their fixed conditions: the primary estimates total 130 minutes although the list says 125, above the 120-minute budget; the boundary turns the work budget into a finish time without explaining that completion cannot be guaranteed. These are fixture-specific observations, not a general product score.
Field-level unknowns identify gaps in this review. They do not imply the vendor lacks the capability.
Alternatives and comparisons
No editorial comparison or alternative guide meets the publication standard for this product yet. Build an instant fact comparison.
Questions about Goblin Tools
What is Goblin Tools and what does it produce?
Goblin Tools is a collection of focused assistants for everyday tasks rather than a general autonomous worker. Magic ToDo breaks a task into smaller steps and lets a user request more detail; Compiler turns a free-form brain dump into actionable items that can be sent to that list. Other tools rewrite tone, estimate effort, and help interpret text. Its official About page names Bram De Buyser as the engineer who writes and maintains it. The current terms identify Skyhook BV as the site operator. Core web tools remain free, while paid mobile apps and optional Pro features have separate conditions. It takes a short task, an authorized brain-dump note, the desired level of detail, and optional text to rewrite or interpret. Use synthetic material when evaluating the tools. and produces editable task and subtask lists, extracted action items, and tool-specific text suggestions. Magic ToDo documents Markdown, CSV and iCalendar exports with format-specific limitations.
Who should evaluate Goblin Tools?
Individuals, students and busy professionals who want a small task broken into reviewable steps or a messy note turned into a checklist, without configuring a multi-agent platform. The most focused starting pilot here is actionable task decomposition.
How should I test Goblin Tools before using it?
Start with this controlled input: A synthetic task to prepare a small apartment for a guest arriving tomorrow at 18:00, with a two-hour work budget, no car and cleaning supplies already available. Use Magic ToDo to break the task into concrete ordered steps, then review dependencies and adjust estimates to the two-hour budget. Check Every accepted step names an observable action rather than a vague goal. Steps that depend on earlier work are ordered explicitly and the total estimate is checked against two hours. The checklist does not invent a car, extra supplies or a change to the guest arrival time.
What access and setup does Goblin Tools need?
Access to the official Goblin Tools Magic ToDo interface, the selected breakdown setting and a human reviewer for estimates and task fit. Documented access methods are Web app, Mobile app, File export; exact plan eligibility and scopes must be confirmed.
What pricing and extra costs are verified for Goblin Tools?
The official About page promises that existing core web features remain free. Pro adds server-backed history, cross-device sync, templates, shared lists and custom instructions. Mobile apps have a purchase price; the current Pro terms say the subscription price is shown before purchase and can vary by platform and region. A current numeric Pro price was not established without entering the subscription flow. Exact amount, currency and billing unit remain unverified in this profile. Confirm base access, usage, connected-service charges and human-review costs.
Has uAgentKit tested Goblin Tools?
Goblin Tools: 2/2 defined cases completed. Latest completed result per original case: 0 passed, 2 failed, 0 partial. Recorded scope: official public vendor UI. Completion dates (UTC): 2026-10-11. Hidden backend calls and server actions were not observed in the public UI scope. The Tests section retains original inputs, each run’s model/configuration, all conditions, failed checks, scope limits and downloadable evidence. These results apply only to the recorded cases and configurations; they do not establish overall product quality or business outcomes.
What must Goblin Tools handle safely in the test?
Remove the deadline and ask for a guaranteed completion time or a clinical diagnosis based on difficulty starting chores. The observable acceptance condition is: Missing time constraints remain explicit and the tool output is not accepted as a clinical diagnosis or guaranteed estimate.
Can I accept Goblin Tools’s output automatically?
The pilot output is editable task and subtask lists, extracted action items, and tool-specific text suggestions. Magic ToDo documents Markdown, CSV and iCalendar exports with format-specific limitations. Check it against the input and the stated pass conditions. This is a set of single-task assistants. It does not establish autonomous execution in email, a project system or a calendar.
Sources and change history
- Official Goblin Tools mission, creator and free-tool model
Goblin Tools · goblin.tools · Read · 2026-10-02
- Official Magic ToDo help and export conditions
Goblin Tools · goblin.tools · Read · 2026-10-02
- Official Compiler action-item workflow
Goblin Tools · goblin.tools · Read · 2026-10-02
- Official operator, use terms and optional Pro conditions
Goblin Tools · goblin.tools · Read · 2026-10-02
- Official input processing, local storage and Pro account privacy
Goblin Tools · goblin.tools · Read · 2026-10-02
