team-fix — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited team-fix (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Run the compressed bug-fix pipeline. Goes straight to test-driven fix discipline without the full QRSPI ceremony.
$ARGUMENTS may be:
ENG-1234) — set aside as ticketId ontask.md.
gh issue view to extract title and body.When $ARGUMENTS is empty, discover, don't demand: ground in repo context before asking. Read recent git log activity and the repo's README / CLAUDE.md to surface the likely failing area, then use AskUserQuestion with labeled options to fill any genuine gap. Never bare-stop with a plain "describe the bug" demand when context is available.
Use /team-fix when:
Use /team (full QRSPI pipeline) when:
REPRODUCE → RED (failing test) → GREEN (minimal fix) → VERIFY → SHIPNo Question. No Research. No Design. No Structure. No Plan. No human gate.
$ARGUMENTS,ground in repo context, then ask only for genuine gaps, per the "discover, don't demand" rule in ## Input. A ticket id or issue URL is resolved as ## Input describes (gh issue view for URLs).
or issue, move that ticket to its tracker's in-progress state — this is the first action of the fix, before any other work begins. Best-effort and tracker-agnostic: if the project defines no tracker-move mechanism (e.g. a free-form bug description, or a tracker the environment can't reach), skip silently and continue. Never block the pipeline on a tracker update.
/team does (ticket-prefixed ordate-prefixed kebab slug). Create docs/plans/<id>/.
docs/plans/<id>/task.md with the standard frontmatter(topic, date, phase: task, ticketId) plus a brief description of the bug. The topic value is the kebab portion of <id> — i.e. <id> minus the <TICKET>- or <YYYY-MM-DD>- prefix. Never use the ticket id, the date, or a re-worded description as the topic. ticketId lives only on task.md. This is the single durable record for the fix and lets any /team-* command pick it up if interrupted.
Reproduce → Red (failing test) → Green (minimal fix) → Verify → Ship. Mark Reproduce as in_progress. See skills/progress-tracking/SKILL.md for the per-step tracking convention agents follow within each phase.
Follow the test-driven-bug-fix methodology from skills/test-driven-bug-fix/SKILL.md. Read that skill before proceeding.
When the failure is non-obvious, Load skills/systematic-debugging/SKILL.md and drill its Root Cause Analysis (5 Whys) causal chain to the root before proposing a fix.
Mark each TodoWrite item in_progress when you begin and completed when it finishes.
Mechanical gate between Red and Green: the new test must fail with an assertion failure, not a crash. Do not proceed to the fix until confirmed.
test: commit with the failing testfix: commit with the minimal fixa branch, push it and open the PR as a draft (gh pr create --draft). If not on a branch, commit to the working branch.
ticketId is non-null in task.md'sfrontmatter: link the PR to the ticket so the tracker closes it — and any board automation moves it to its done state — when the PR merges (GitHub: Closes #<n> in the PR body); then move the ticket to the tracker's in-review state. Best-effort and tracker-agnostic — skip silently if the project defines no tracker-move mechanism; never block. Because the link auto-closes the ticket on merge, the orchestrator never closes tickets by hand. Surface the ticketId in the completion report.
If reproduction fails: report "Bug could not be reproduced with the given description." and stop. Do not write a test for an unconfirmed bug.
If the fix is larger than expected (touching many files, requiring new APIs, or revealing an architectural problem): stop, report the scope, and recommend switching to the full /team pipeline.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.