Borrowing it
Nothing to install: this file belongs to marcoguillermaz/Tierward. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcoguillermaz/Tierward/main/.claude/skills/repo-hygiene/SKILL.mdgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/repo-hygiene)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/repo-hygiene"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/repo-hygiene/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/marcoguillermaz/tierward/repo-hygiene"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/repo-hygiene.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 | $0.00168 | $0.02790 |
| Opus 5 | $0.00084 | $0.01395 |
| Sonnet 5 | $0.00034 | $0.00558 |
| Haiku 4.5 | $0.00017 | $0.00279 |
Grade C, and why
repo-hygiene scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Bash(rm -rf .claude/worktrees/*), How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tierward repo variant - diverges deliberately from the scaffolded payload copy (packages/cli/templates/tier-{m,l}/...): adds the unregistered-worktree-dir scan, Step 2b (initiatives staleness), and the docs/reviews/ staleness pass. Do not sync this file back over the payload copies.
Runs in the main conversation, deliberately without context: fork. AskUserQuestion is unavailable to subagents/forked skill contexts, and this skill's confirm-then-execute design requires it mid-run. Do not add context: fork to this file.
Goal: search thoroughly, report every candidate with concrete evidence, execute only what the user explicitly confirms. Never guess-execute. Never touch docs/*.md regardless of confirmation.
Step 0 - Parse scope
$ARGUMENTS: default = quick scan (Steps 1, 2, 2b). target:full adds Step 3 (doc orphans + reviews staleness) - the slow, judgment-heavy pass. target:reviews runs ONLY the Step 3 reviews-staleness pass (skips the tracked-doc orphan sweep). State which mode is active before starting.
Always exclude .claude/worktrees/** from every Grep/Glob in Steps 2 and 3. Worktrees are full repo checkouts - without this exclusion every file inside every active worktree gets reported as a duplicate "root-level" finding.
Step 1 - Branch & worktree scan (mechanical, always runs)
Run the companion script:
bash .claude/skills/repo-hygiene/references/scan-branches-worktrees.sh
It is read-only and prints three sections:
SAFE_BRANCH_DELETE- bare branch names with no attached worktree, merged into every protected branch that exists on origin (seePROTECTED_BRANCHESat the top of the script), no open PR.SAFE_WORKTREE_REMOVE-<branch>|<path>pairs, merged into all protected branches, clean working tree, no open PR. Lines prefixedKEEP|are explicitly excluded with a reason (uncommitted changes / not yet merged / open PR / gh check failed) - do not re-litigate these, the script already checked.PRUNABLE_WORKTREE- paths registered ingit worktree listwhose actual directory no longer exists.ORPHAN_WORKTREE_DIR- directories on disk under.claude/worktrees/that are NOT registered ingit worktree list(leftovers of a failed/manual removal + prune), with a content summary (files:N|newest:date). Git cannot report dirtiness for an unregistered dir, so these NEVER join the low-risk batch: each one gets its own separate confirmation in Step 5, after the content summary is shown, and is removed withrm -rfonly on that explicit per-item confirm.
What ships with it
1 file 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.
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.
- 12d ago First seen · 106 lines · 168 tokens per session scan C 15095ce97ffc
repo-hygiene is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 5d ago), licensed MIT. It adds 168 tokens to every session and 2,790 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-hud
Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.
create-pr
Create a pull request from the current branch with structured summary.
git-commit
Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.
install
This skill should be used when the user asks to "install pikiclaw", "build and install", "deploy locally", "update local binary", "release", or "publish".
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
github-pr-comment
Post one exact GitHub pull-request comment through local gh, any compatible hosted connector, or the explicit human-gated MCP composition, with retry safety and independent readback.