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 glebis/claude-skills --skill repo-prepgit clone --depth 1 https://github.com/glebis/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/glebis/claude-skills/repo-prep)<a href="https://agentmods.dev/skills/glebis/claude-skills/repo-prep"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/repo-prep/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/glebis/claude-skills/repo-prep"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/repo-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00158 | $0.01518 |
| Opus 5 | $0.00079 | $0.00759 |
| Sonnet 5 | $0.00032 | $0.00304 |
| Haiku 4.5 | $0.00016 | $0.00152 |
Grade A, and why
repo-prep 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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Prep
Interactively scaffold the legal, metadata, community, and compliance files a repository needs before publication — consistently, from a central author profile, with author choices respected per repo.
When to use
- Preparing a new or existing repo for GitHub / open-sourcing.
- Adding missing LICENSE, NOTICE, AUTHORSHIP, README sections, or package metadata.
- Writing a defensible AUTHORSHIP record for AI-assisted work (the wizard).
- Adding community docs or
.github/templates. - Checking EU/Germany compliance obligations for a repo.
Operating principles
- Interactive, not assumed. Ask the user for choices (see Asking questions
below); respect the author profile's
defaultsbut confirm per repo. Don't blindly dump templates. - Idempotent. Detect what already exists; skip or refresh, never clobber silently. Show a plan before writing.
- Evidence over assertion (especially authorship): mine the repo for facts.
- Confirm outward-facing actions (anything via
gh, pushes) before running. - Follow the user's git conventions — commit only when asked.
Asking questions (interview transport)
Prefer cenno when it is installed — it gives a nicer panel, progress dots, and voice input (great for the reflective authorship answers).
- Detect cenno once per run:
ToolSearchformcp__cenno__ask_sequence. If the tools resolve, use cenno; otherwise fall back toAskUserQuestion(choices) / plain conversational prompts (free text). - When using cenno:
- Multi-question flows (the authorship wizard, scope selection) →
mcp__cenno__ask_sequencewithflow: "question"; it auto-fills progress dots. - Single questions →
mcp__cenno__ask_user. - Use
input.kind: "choice"+choicesfor pick-one;"confirm"for yes/no;"voice_text"for reflective free-text (Decisions, Judgment, Direction, Art Direction);"scale"for ratings. - Parse the returned JSON (
{answers: [...]}/{answer, ...}). Handle{answered: false}(timeout) by retrying or falling back.
- Multi-question flows (the authorship wizard, scope selection) →
- If cenno is wanted but not installed, mention it can be set up via the
cennoskill; do not block — fall back gracefully.
What ships with it
20 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.
- assets/github/dependabot.yml 358 B
- assets/github/ISSUE_TEMPLATE/bug_report.md 469 B
- assets/github/ISSUE_TEMPLATE/feature_request.md 396 B
- assets/github/pull_request_template.md 153 B
- assets/github/workflows/ci-node.yml 578 B
- assets/github/workflows/ci-python.yml 629 B
- assets/licenses/BSD-3-Clause.txt 1.5 KB
- assets/licenses/MIT.txt 1.0 KB
- assets/templates/AUTHORSHIP.md 2.7 KB
- assets/templates/CHANGELOG.md 271 B
- assets/templates/CODE_OF_CONDUCT.md 952 B
- assets/templates/CONTRIBUTING.md 1.6 KB
- assets/templates/NOTICE.txt 427 B
- assets/templates/profile.example.toml 1.7 KB
- assets/templates/SECURITY.md 530 B
- references/authorship-wizard.md 7.0 KB
- references/checklist.md 4.0 KB
- references/eu-germany-compliance.md 7.3 KB
- references/licenses.md 1.6 KB
- scripts/fetch_license.py 2.5 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.
- 8d ago First seen · 117 lines · 158 tokens per session scan A 73dcfaca80bc
repo-prep is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 158 tokens to every session and 1,518 once invoked, about $0.0008 per session on Opus 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 2026-09-03.
Other skills, from other repositories
open-sourcing
This skill should be used when the user asks to "open source this project", "prepare this repository for public release", "make this repo public", "check open-source readiness", "choose a license for this project", or "set up release automation" ahead of a public launch. Provides a release-readiness workflow covering…
compliance-license-audit
Interactive open-source license compliance audit to identify all dependency licenses, flag risks, and detect license incompatibilities.
compliance-notice-generate
Generate NOTICE, ATTRIBUTION, or THIRD-PARTY-NOTICES files from detected dependency licenses to fulfill open-source license obligations.
open-source
Open source readiness best practices. Covers licensing, documentation, community health, CI/CD, compliance, legal, and packaging. USE WHEN: user mentions "open source", "license", "LICENSE", "CONTRIBUTING", "CODEOFCONDUCT", "CHANGELOG", "open source readiness", "community health", "OSS compliance", "SPDX", "CLA"…
community-health
Guide for setting up GitHub community health files for open source repositories. Use when preparing repos for public release, adding community standards files, or configuring issue/PR templates.
release-guard
Block releases that fail the licence and changelog policy, and bundle the team's release tooling into one installable package.