Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sailingnaturali/claude-skills --skill repo-scaffoldgit clone --depth 1 https://github.com/sailingnaturali/claude-skillsWrote 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/sailingnaturali/claude-skills/repo-scaffold)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/repo-scaffold"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/repo-scaffold/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/sailingnaturali/claude-skills/repo-scaffold"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/repo-scaffold.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 | $0.00175 | $0.05696 |
| Opus 5.5 | $0.00070 | $0.02278 |
| Sonnet 5.5 | $0.00035 | $0.01139 |
| Haiku 4.5 | $0.00017 | $0.00570 |
Grade A, and why
repo-scaffold 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 13d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo scaffolding that pays rent
Six pieces of scaffolding, each of which has already paid for itself in a maintained repo. Copy the shapes; the rationale is what keeps them from being cargo cult.
1. Agent context: AGENTS.md, imported by CLAUDE.md
Repo conventions (architecture, invariants, workflow rules) live in AGENTS.md — the
vendor-neutral file that multiple coding agents read. CLAUDE.md then contains exactly one
line:
@AGENTS.md
The @ import syntax matters: it inlines the whole file into the agent's context at
session start. A plain markdown link (See [AGENTS.md](AGENTS.md).) is not followed
automatically — observed side by side in two live repos: the @-import version loaded the
full conventions, the link version loaded only the one-line stub. If your conventions aren't
reaching the agent, check which form the repo uses.
2. .gitattributes: one line ends a whole failure class
* text=auto eol=lf
Prettier and eslint enforce LF. Without this line, Windows CI runners (and contributors with
core.autocrlf) check out CRLF and prettier --check fails on every line with
Delete `␍` — a wall of red unrelated to the change. Related Windows-runner trap: npm
script globs must be double-quoted ("dist/test/*.test.js") or Windows expands them.
3. Format locally, verify in CI
Two package.json scripts, one writing, one read-only:
format—prettier --write . && eslint --fix(the developer's command)ci-lint—eslint && prettier --check .(what CI runs — read-only, so uncommitted format drift fails the build instead of being silently "fixed")
Wire ci-lint into the PR workflow of every repo, including ones that started as pure
docs/shell — retrofitting it later means a noisy reformat commit. After bumping prettier /
eslint / typescript versions, run npm install before format: formatter output diverges
between versions and CI will reject stale-toolchain output.
4. Container repos: a weekly Trivy scan, tuned to be actionable
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.
- 13d ago Changed · +185 lines c2231f38be48
- 1mo ago First seen · 189 lines · 175 tokens per session scan A f12422b91316
repo-scaffold is a skill published in the GitHub repository sailingnaturali/claude-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 175 tokens to every session and 5,696 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
factory-ship
Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.
gitlab-devops
GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…
seed-snapshot-release
An automated workflow for creating and tracking a snapshot release of the pull request on the current branch. A snapshot release is a temporary package build used for testing a branch before a normal release.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
ct-release-orchestrator
Orchestrates the canonical 4-verb release pipeline introduced by SPEC-T9345: cleo release plan, then cleo release open, then PR + GHA tag workflow, then cleo release reconcile. The deprecated cleo release ship monolith was deleted in T10103 — do not invoke it. Use ship-e2e-smoke to validate the full pipeline…
cmux-release
Prefer the /release command. It determines the new version (minor by default), gathers the Changelog line from each PR merged since the last stable tag, updates CHANGELOG.md, runs ./scripts/bump-version.sh, commits, runs ./scripts/release-pretag-guard.sh, then tags and pushes.