Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install playbooksWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/melodic-software/claude-code-plugins/repo-sweep)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/repo-sweep"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/repo-sweep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/repo-sweep"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/repo-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.01743 |
| Opus 5.5 | $0.00052 | $0.00697 |
| Sonnet 5.5 | $0.00026 | $0.00349 |
| Haiku 4.5 | $0.00013 | $0.00174 |
Grade A, and why
repo-sweep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-sweep
Runs the skills in catalogs/hygiene.md, in file order, against the current repository. The
catalog is the only home for which skills run, their order, arguments, applies-when tests,
default checked state, and override text; changing a sweep means editing the catalog.
Invocation
| Invocation | Action | Procedure |
|---|---|---|
/playbooks:repo-sweep plan |
Recommend per entry, open the selection page, create the sweep branch and draft PR | reference/plan.md |
/playbooks:repo-sweep next |
Run the first unticked step: audit, review findings with the user, fix, one commit, tick | reference/next.md |
/playbooks:repo-sweep review |
Ask what went wrong in the last step; audit and file each problem after approval | reference/review.md |
No argument: run state.sh (below). Exit 10 or 11 means plan; exit 0 means next. Say
which you chose.
Read the matching procedure file before acting. Each action runs in a fresh session: next and
review rebuild all state from the PR body and the branch, never from the conversation.
Scripts
All under ${CLAUDE_SKILL_DIR}/scripts/. Exit 2 is a usage error everywhere; codes 10 and up
carry the meanings below; any other non-zero code is a failed gh, git, or jq call.
| Script | Does | Exit codes |
|---|---|---|
catalog.sh <catalog> |
TSV per entry: id, phase, skills, args, checked, issue, applies-when. --override <id> / --notes <id> print that block |
1 duplicate id, missing skill, unknown id |
skill-version.sh <plugin:skill>... |
plugin:skill@version; @builtin without a plugin prefix, @unknown when not installed |
0 |
history.sh <catalog> |
TSV id, recommendation (run, rerun, rerun-optional), reason, from merged sweep PRs then Playbook-Step trailers |
1 catalog error |
render.sh --checklist <catalog> <selection-line> [<recs-tsv>] |
The PR checklist block plus Not run: |
1 bad id, selection, or TSV |
render.sh --page <catalog> <recs-tsv> |
The filled selection page on stdout | 1 as above, or template missing |
state.sh |
key value lines: pr, branch, pr-state, playbook, dirty, untick-committed <id> <sha> <skill@version>..., done-unverified <id>, next <id> in-progress|pending, sweep <n> <branch> |
0 next step found; 1 no markers; 10 no sweep PR; 11 PR merged or closed; 12 dirty tree, step pending; 13 all done; 14 one open sweep on another branch; 15 several open sweeps |
tick.sh <id> in-progress / committed <sha> <skill@version>... / no-findings <skill@version>... |
Sets that checklist line, re-reads the body to confirm | 1 line missing, already done, or edit did not land |
guard.sh <base-sha> <pr-snapshot-file> |
Checks a step stayed on the branch and opened no PR | 10 stop (prints branch-changed, base-not-ancestor, new-pr lines); 11 prints squash git reset --soft <base-sha> |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- catalogs/hygiene.md 7.0 KB
- evals/evals.json 4.7 KB
- reference/next.md 5.7 KB
- reference/plan.md 4.8 KB
- reference/review.md 1.0 KB
- scripts/catalog.sh 2.3 KB runs code
- scripts/catalog.test.sh 3.9 KB runs code
- scripts/guard.sh 1.7 KB runs code
- scripts/guard.test.sh 3.0 KB runs code
- scripts/history.sh 3.8 KB runs code
- scripts/history.test.sh 5.1 KB runs code
- scripts/render.sh 5.5 KB runs code
- scripts/render.test.sh 5.2 KB runs code
- scripts/skill-version.sh 1.8 KB runs code
- scripts/skill-version.test.sh 3.6 KB runs code
- scripts/state.sh 5.4 KB runs code
- scripts/state.test.sh 7.0 KB runs code
- scripts/testdata/checklist.golden.txt 267 B
- scripts/testdata/fixture.md 624 B
- scripts/tick.sh 2.8 KB runs code
- scripts/tick.test.sh 3.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago First seen · 110 lines · 129 tokens per session scan A 4851872a522a
repo-sweep is a skill published in the GitHub repository melodic-software/claude-code-plugins (28 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 1,743 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
team-workspace
Set up or work with a git-backed team workspace for co-owned artifacts — charters, strategy docs, decision records — separate from private reflections. Triggers: "share our team charter with the team", "set up a shared haku workspace", "put our strategy doc in the team repo", "how do teams use haku together".…
omh-github-issue-intake
This is an OMH github-issue-intake workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
jira-execute
Implement a Jira issue, open a pull request, and report the work on the issue. Insert into the prompt of a Jira column rule that does the building.