status
Skill1 starsChanged 8 months agoMITView on GitHub
Code Cannon: Summarize in-progress and recently completed work from GitHub and git
177 other projects use a version of this.
Adopted by
Most recently taken up by
- zaynram/scholartheir own version, first seen Nov 8, 2026
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- leinardi/adversarial-review-looptheir own version, first seen Nov 8, 2026
- emotixco/claude-skills-foundertheir own version, first seen Nov 8, 2026
- flung-official/flung-claude-plugintheir own version, first seen Nov 8, 2026
Used with
Projects with it also use off, list and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
StakeholderSenseiSkilloff
Disable polygraph for this repo (user-only escape hatch; all hooks no-op)
Also in 4 projects that use this
SuShuhengSkilllist
Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.
Also in 8 projects that use this
kennethleungtySkillpause
Pause — stop the music (alias for /stop)
Also in 6 projects that use this
codebycoreySkillnew
Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.
Also in 7 projects that use this
michaelenglandSkillimport
This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.
Also in 5 projects that use this
genomewalkerSkillresume
Resume a thread by loading its ~800-token context capsule
Also in 15 projects that use this
Other versions177 projects use a version of this.
Word for word · 1
- sebastientaggart/CodeCannon★ 1100% same
Edited · 0
None found.
Wrote their own version · 176
- anthropics/claude-for-legal★ 9.5ksame name
- microsoft/TokenEconomizer★ 5ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- H-mmer/pentest-agents★ 815same name
- emotixco/claude-skills-founder★ 796same name
- me2resh/apexyard★ 542same name
- dsifry/metaswarm★ 426same name
- ffroliva/gflow-cli★ 367same name
- serithemage/serverless-openclaw★ 196same name
166 more not listed
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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- checkpointSkill
- delegateSkill
- deploySkill
- qaSkill
- reviewSkill
- setupSkill
- startSkill
- statusSkill
- storySkill
- submit-for-reviewSkill
- checkpointSkill
- delegateSkill
- deploySkill
- qaSkill
- reviewSkill
- setupSkill
- startSkill
- storySkill
- submit-for-reviewSkill
- checkpointSkill
- delegateSkill
- deploySkill
- qaSkill
- review-agentSkill
- reviewSkill
- setupSkill
- startSkill
- statusSkill
- storySkill
- submit-for-reviewSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 145 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Run these concurrently. If any gh command exits non-zero (including auth errors), report the message and stop — do not retry.
- Distinctive: line 96
If none match, omit the "what's next" section.
- Distinctive: line 109
If the issue query fails (milestone not found, auth error), report and stop.
- Distinctive: line 131
If either fails, report and stop.
- Distinctive: line 141
Never write to GitHub (no comments, labels, issue updates, or PR changes) and never touch the working tree.
- Very specific: line 142
If gh is unauthenticated or any fetch fails, report the error and stop immediately.
“Common” is measured: kept by at least 6 in 10 of the 145 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
What /status does
/status prints a read-only, standup-ready snapshot of in-progress and recently completed work, then a single "what's next" suggestion. It never writes to GitHub or the working tree — it only reads and reports.
Because it is read-only, the shape of its output does not matter: a differently-formatted-but-accurate summary is a fine result. Derive a clear, scannable layout yourself. What this skill pins down is the data to fetch, how to classify it, and the one piece of real opinion — the "what's next" ordering.
Step 1 — Determine mode
Three mutually exclusive modes, selected from $ARGUMENTS:
- Milestone mode —
--milestoneor--sprintis present. Everything after the flag is the milestone name (a name or a number; trim outer whitespace, preserve internal spaces). Ignore other arguments. Run Steps M1–M2. - Team mode —
--teamis present. Run Steps T1–T2.--teamis mutually exclusive with--milestone/--sprintand with a username; if combined, report the conflict and stop. - Personal mode — no mode flag. Subject defaults to
@me; a@nameor a non-numeric word is a username (strip the leading@forghflags that reject it, keep it for display). Lookback defaults to7; a bare number is the lookback in days.
Step 2 — Fetch GitHub data (personal mode)
Run these concurrently. If any gh command exits non-zero (including auth errors), report the message and stop — do not retry.
Open PRs authored by subject — request enough fields to derive health (draft, CI, review decision, merge conflict) and staleness:
gh pr list --author <subject> --state open \
--json number,title,url,labels,milestone,baseRefName,body,reviewDecision,statusCheckRollup,updatedAt,mergeable,isDraftRecently merged PRs, filtered to those merged within <lookback> days:
gh pr list --author <subject> --state merged --limit 20 \
--json number,title,url,mergedAt,labels,baseRefNameOpen issues assigned to subject:
gh issue list --assignee <subject> --state open \
--json number,title,url,labels,milestone,updatedAtPRs requesting your review — only when subject is @me; skip for other users:
gh pr list --search "review-requested:@me" --state open \
--json number,title,url,author,updatedAtAlso fetch local git context (skip and note if not in a git repo — git rev-parse --is-inside-work-tree):
git log --oneline --since="<lookback> days ago"Step 3 — Classify and report (personal mode)
Sort items into these buckets:
- In progress — open PRs. Identify a linked issue from the PR body (
#N,closes #N,fixes #N,issue #N) and cross-reference open issues. - Done — PRs merged within the lookback window.
- Up next — open issues whose number is not referenced by any open PR body. (An issue linked from an open PR belongs under In progress with that PR, not here.)
- Needs your review — the review-requested query (only when subject is
@me).
For each open PR, derive health from the JSON — draft state, CI status from statusCheckRollup, review state from reviewDecision, merge conflict from mergeable. Present each as a compact badge; omit a badge when it does not apply or is not configured.
Staleness: flag any open PR or issue not updated within 14 days (a threshold of 0 disables staleness entirely). Note the last-updated date and age. This is a real config-driven rule — honor the threshold exactly.
Report the buckets as a scannable summary: a heading naming the subject and lookback, a one-line count roll-up, then a section per non-empty bucket, then the local commits (or a note that git was skipped). Show labels/milestone only when present; dates as YYYY-MM-DD. If every GitHub bucket is empty, say so plainly for the subject and window.
Do not post, comment, write files, or take any action. Output only.
Step 4 — What's next (personal mode)
After the summary, append one actionable suggestion. Gather the extra local state you need (current branch, git status --porcelain, latest tag via git describe --tags --abbrev=0, unreleased commit count via git rev-list <tag>..HEAD --count, and the current branch's PR review/check state via gh pr view — treat a non-zero exit as "no PR for this branch"). Skip git lookups when not in a repo.
Evaluate these conditions in order and use the first match. This ordering is the workflow's opinion about what the operator should do next — it is load-bearing, not formatting:
| Priority | Condition | Suggestion |
| 1 | On a feature/* branch with uncommitted changes | You have uncommitted changes on <branch>. When ready, run /submit-for-review. |
| 2 | On a feature/* branch, open PR is APPROVED and all checks COMPLETED | PR #<number> is approved and checks pass. Consider running /deploy. |
| 3 | On a feature/* branch with an open PR in any other state | PR #<number> (<title>) is open and awaiting review. |
| 3.5 | Subject is @me and PRs request your review | Append to the current suggestion (or stand alone if nothing higher matched): You also have <N> PR(s) awaiting your review. |
| 4 | On a feature/* branch, no open PR, clean tree | No open PR for <branch>. Run /submit-for-review to open one. |
| 5 | On the integration branch with unreleased commits since the last tag | <N> commit(s) on <branch> since <tag>. Run /deploy when ready to release. |
| 6 | No open PRs and no open issues assigned to subject | Nothing in progress. Run /start to begin new work. |
| 7 | Open issues exist in "Up next" | Next up is #<number> (<title>). Run /start <number> to pick it up. |
If none match, omit the "what's next" section. Omit it entirely in milestone mode.
Milestone mode (Steps M1–M2)
M1 — Fetch
gh issue list --milestone "<name>" --state all --limit 200 \
--json number,title,state,labels,assignees,url
gh pr list --state open \
--json number,title,body,baseRefName,reviewDecision,statusCheckRollup,mergeable,isDraftIf the issue query fails (milestone not found, auth error), report and stop.
M2 — Classify and report
Group the milestone's issues into three buckets:
- Done —
state: closed. - In progress — open, and the issue number is referenced by some open PR body (
#N,closes #N,fixes #N,related to #N,issue #N). This "referenced by an open PR" definition is the real rule — apply it exactly. - Not started — open, and no open PR references it.
Derive health badges for in-progress issues from their linked PR (same fields as personal mode). Report as a scannable summary titled with the milestone name and a closed/in-progress/not-started roll-up. Show assignees and URLs where they add value; omit empty buckets. Do not post, comment, write files, or take any action. Output only.
Team mode (Steps T1–T2)
T1 — Fetch (run both concurrently)
gh pr list --state open --limit 100 \
--json number,title,url,author,labels,milestone,baseRefName,body,reviewDecision,statusCheckRollup,updatedAt,mergeable,isDraft
gh issue list --state open --limit 200 \
--json number,title,url,assignees,labels,milestone,updatedAtIf either fails, report and stop.
T2 — Group and report
Group by person: PRs by author.login; issues by first assignee (unassigned issues into an "Unassigned" group). Within each person, classify as personal mode does — in progress (open PRs and their linked issues) and up next (open issues not referenced by any open PR) — and derive health badges plus staleness. Report per-person sections with in-progress items first, an "Unassigned" section if any, and a consolidated stale section. Do not post, comment, write files, or take any action. Output only.
Hard rules
- Never write to GitHub (no comments, labels, issue updates, or PR changes) and never touch the working tree. Output only.
- If
ghis unauthenticated or any fetch fails, report the error and stop immediately. Do not retry. - Strip the leading
@from the subject when passing toghflags that reject it. --teamis mutually exclusive with--milestone/--sprintand with a username.- The
14threshold is config-driven;0disables staleness. The "what's next" priority ordering is fixed — evaluate top to bottom, first match wins.
<!-- generated by CodeCannon/sync.py | skill: status | adapter: claude | hash: 22a25479 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->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.

