next-task
Skill1 starsChanged 10 days agoApache-2.0View on GitHub
Pick the next unblocked task from docs/roadmap.md (or the task ID given) and carry it through the project's definition of done, leaving changes uncommitted for review.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- Destrayon/Connapsetheir own version, first seen Nov 7, 2026
- Integralist/agent-skillstheir own version, first seen Nov 6, 2026
- Appuator/Skillstheir own version, first seen Oct 25, 2026
- Vernum-Projecten/cc-shifttheir own version, first seen Oct 20, 2026
- microsoft/devsquad-copilottheir own version, first seen Oct 16, 2026
- enapt/SwarmLLMtheir own version, first seen Oct 16, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- breaking-brake/cc-wf-studio★ 5.4ksame name
- enapt/SwarmLLM★ 82same name
- microsoft/devsquad-copilot★ 50same name
- Integralist/agent-skills★ 23same name
- Destrayon/Connapse★ 22same name
- Nirusan/claude-config★ 7same name
- Vernum-Projecten/cc-shift★ 2same name
- Appuator/Skills★ 0same name
- Freakling/Director-Driven-Development★ 0same name
- rckycls/mvp-to-tasks★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-ffi-bindingSkill
- add-managed-toolSkill
- evaluate-dependencySkill
- record-decisionSkill
- verifySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
24 rules. 0 are common, 12 are distinctive, and 12 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
If a task ID was given, use it.
- Very specific: line 21
If the task has a Decide first line, ask each question in it before writing code, unless docs/decisions.md already records the answer:
- Distinctive: line 39
Read the docs that AGENTS.md → "Read before working" lists for the crates the task touches, starting with each crate's README.md.
- Distinctive: line 41
Read the existing code in those crates before writing new code.
- Distinctive: line 44
If the spec and the code disagree, or the spec is ambiguous in a way that changes a public API, a file format, a protocol or the dependency …
- Very specific: line 50
Do exactly what the task's Do lines and acceptance criteria require.
- Distinctive: line 51
Use the subagent that owns the crate (table in CLAUDE.md).
- Very specific: line 52
New third-party crate needed?: Stop and run /evaluate-dependency.
- Very specific: line 53
OS bindings needed?: Follow /add-ffi-binding.
- Very specific: line 54
A new or changed outside tool?: Follow /add-managed-tool.
- Very specific: line 55
A design decision changed?: Run /record-decision and update the affected docs.
- Distinctive: line 57
Write the tests the acceptance criteria call for, beside the code.
- Distinctive: line 58
Start every new source file with the license header (ADR-0021).
- Very specific: line 59
Ask security-reviewer to review when the change touches sys, platform, toolchain, mobile, agent, or any parser.
- Distinctive: line 61
If the change spreads beyond three crates, pause and tell the user the task may be mis-scoped.
- Very specific: line 66
Run every command in the task's Verify line.
- Distinctive: line 73
Do everything possible here.
- Distinctive: line 74
Leave the box unchecked.
- Very specific: line 75
Add an indented ⏳ needs <OS/tool>: <exact remaining check> line under the task.
- Distinctive: line 80
Check the box only if every acceptance criterion is met and every verification command ran and passed in this session.
- Very specific: line 82
Add brief indented Note: lines under the task where useful: pinned versions, measured numbers, tool facts checked and their sources.
- Very specific: line 84
Update the README.md of every crate whose built state changed: its ## Status names the task (ADR-0023).
- Distinctive: line 86
Update docs only where behavior or design actually changed.
- Distinctive: line 90
Leave all changes uncommitted.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Work the next roadmap task
Requested task: $ARGUMENTS (empty means "pick the next unblocked task").
1. Choose the task
- Open
docs/roadmap.md. - If a task ID was given, use it. If its
Dependstasks are not all checked, stop and tell the user which ones block it. - Otherwise, take the first unchecked task whose
Dependsare all checked.- Skip a task whose remaining work is marked
⏳ needs <OS/tool>when this session can't provide it. Mention any task you skipped and why.
- Skip a task whose remaining work is marked
If the task has a
Decide firstline, ask each question in it before writing code, unlessdocs/decisions.mdalready records the answer:- for a
ProposedADR, present its decision and alternatives in a few sentences and ask whether to accept it; - for any other question, lay out the options the line names, with their costs, and recommend one.
Record each answer with
/record-decision(accept, supersede, or a new or extended ADR) before writing code. If the user is not there to answer, stop after the preparatory reading and say what is waiting.- for a
- Tell the user in one or two sentences which task you're starting and how you plan to approach it. Create a task list whose last item is "Verify and report".
2. Load context, and only the context you need
AGENTS.mdis already loaded. Re-read its "Non-negotiable rules" if unsure.- Read the docs that
AGENTS.md→ "Read before working" lists for the crates the task touches, starting with each crate'sREADME.md. - Read the existing code in those crates before writing new code. Follow established patterns and naming. Where the task says to port from Nadir, read the matching Nadir code first and port it with a note.
- If the spec and the code disagree, or the spec is ambiguous in a way that changes a public API, a file format, a protocol or the dependency matrix: stop, describe the conflict, propose the safest option, and ask.
3. Implement the smallest complete change
- Do exactly what the task's
Dolines and acceptance criteria require. - Use the subagent that owns the crate (table in
CLAUDE.md). - New third-party crate needed? Stop and run
/evaluate-dependency. - OS bindings needed? Follow
/add-ffi-binding. - A new or changed outside tool? Follow
/add-managed-tool. - A design decision changed? Run
/record-decisionand update the affected docs. - Write the tests the acceptance criteria call for, beside the code.
- Start every new source file with the license header (ADR-0021).
- Ask
security-reviewerto review when the change touchessys,platform,toolchain,mobile,agent, or any parser. - If the change spreads beyond three crates, pause and tell the user the task may be mis-scoped.
4. Verify honestly
- Run every command in the task's
Verifyline. - Then run
/verify(cargo xtask ci). - Fix failures by fixing the code. Never weaken a lint, delete or
#[ignore]a test, raise a tolerance, or re-bless goldens to make a check pass, unless the user explicitly agrees. - Criteria that need another OS, a real tool, a device or manual
observation:
- Do everything possible here.
- Leave the box unchecked.
- Add an indented
⏳ needs <OS/tool>: <exact remaining check>line under the task.
5. Update the roadmap and docs
- Check the box only if every acceptance criterion is met and every verification command ran and passed in this session.
- Add brief indented
Note:lines under the task where useful: pinned versions, measured numbers, tool facts checked and their sources. - Update the
README.mdof every crate whose built state changed: its## Statusnames the task (ADR-0023). - Update docs only where behavior or design actually changed.
6. Do not commit
Leave all changes uncommitted. Do not commit, amend, rebase, tag or push.
7. Report
- Task: ID and title, and whether its box is now checked.
- Changes: what changed, and the files affected.
- Validation: each command run, with its real result.
- Not run: checks that weren't run, and why. Include
⏳items. - Assumptions you made.
- Unresolved issues and residual risks.
- Commit message: a proposed message in the repository's style: the
area first, then the summary and the task ID, as in
text: encodings and atomic save (M1.3)(CONTRIBUTING.md→ "Commits and pull requests"). - Next: the next unblocked task ID.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

