followup-tracking
Skill0 starsChanged 5 months agoMITView on GitHub
Capture deferred decisions, accepted drift, and cross-cutting TODOs in a durable follow-ups log instead of letting them rot in code comments — with a stable-ID entry format and a close/archive lifecycle
1 other project uses a version of this.
Adopted by
Most recently taken up by
- aizech/clinical-skillstheir own version, first seen Apr 19, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- aizech/clinical-skills★ 4same 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 repository29 other files it gives its agents.
- adopt-existing-projectSkill
- adrSkill
- branch-conflict-checkSkill
- ci-watchSkill
- compound-learningsSkill
- config-auditSkill
- cost-checkSkill
- coverage-ratchetSkill
- doc-syncSkill
- eval-harnessSkill
- flaky-triageSkill
- incident-captureSkill
- kit-doctorSkill
- kit-updateSkill
- logging-initSkill
- migration-checkSkill
- new-project-bootstrapSkill
- nightly-auditSkill
- observability-checkSkill
- parallel-workSkill
- perf-budgetSkill
- pr-babysitterSkill
- pre-prSkill
- prompt-regressionSkill
- releaseSkill
- session-handoffSkill
- sync-healthSkill
- using-the-kitSkill
- writing-kit-skillsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 62
Close: when the work lands: mark ✅ RESOLVED <date> inline, then move the entry to docs/followups-archive.md so the active file stays short.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Follow-up Tracking
Profile-driven. The followups file lives at <docs.dir>/followups.md, where docs.dir is capabilities.docs.dir from .claude/kit.yaml (default: docs).
A TODO in a code comment is invisible the moment the PR merges. This skill keeps
deferred work in one durable, greppable place — docs/followups.md — so it gets
addressed on purpose later instead of being rediscovered by accident. Run it when
finishing any unit of work.
What belongs here
- Deferred decisions — "we chose X for now; revisit when Y lands."
- Accepted drift — code intentionally diverges from the spec, spec update
deferred (
spec-update-pending). - Trigger-gated work — don't build it speculatively; note the condition that should trigger it.
- Cross-cutting cleanups — too big for this PR, shouldn't be forgotten.
What does not belong: a bug (file it / fix it), or work you'll do in this same PR (just do it).
Entry format
Append to <docs.dir>/followups.md (capabilities.docs.dir from kit.yaml, default: docs). Every entry has a stable ID so design docs and
commit messages can reference it:
### <ID> — <short title>
- **Spec:** `<path/to/spec.md> §<N.M>` (or the design doc + anchor)
- **Status:** open | open (deferred) | open (trigger-gated) | spec-update-pending
- **Gap:** <2–5 sentences: what the code does now, what it should do, what action
is needed, and — if trigger-gated — the condition that should prompt it.>Choose an ID prefix that groups related items (e.g. S12 = slice 12, AUTH =
auth subsystem, TI-FU3 = time-intent follow-up). Keep IDs stable once assigned.
Example
### S07 — recurring-intent routing is a stub
- **Spec:** `spec_v3.md §25`
- **Status:** open (deferred to Plan 2/3)
- **Gap:** The router returns AUTOMATION for kind="recurring", but the scheduler
only logs and skips — nothing creates the recurrence yet. Wire the handoff when
the constraint slice lands.Lifecycle
- Add at the end of a slice/PR: scan your diff, append entries. The
pre-pranddoc-syncskills both prompt for this. - Reference by ID from PRs and design docs so the thread is traceable.
- Close when the work lands: mark
✅ RESOLVED <date>inline, then move the entry todocs/followups-archive.mdso the active file stays short.
Output
## Follow-ups
- Added: <IDs + titles / none>
- Closed: <IDs / none>
- Active count: <n>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.

