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 agentmods add skills/bidiche49/claude-conf/setup-projectnpx skills add Bidiche49/claude-conf --skill setup-projectgit clone --depth 1 https://github.com/Bidiche49/claude-confWrote 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/bidiche49/claude-conf/setup-project)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/setup-project"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/setup-project.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00987 |
| Opus 5 | $0.00010 | $0.00494 |
| Sonnet 5 | $0.00004 | $0.00197 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade B, and why
setup-project scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Target: `.claude/settings.json` in the PROJECT directory (NOT `~/.claude/settings.json`). How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap this project for Claude Code. Follow these 6 phases in order.
Phase 1 — Detect Stack
Scan project root for config files and identify the stack:
| File | Stack | Permissions | Lint | Test |
|---|---|---|---|---|
pubspec.yaml |
Flutter/Dart | Bash(flutter *), Bash(dart *) |
flutter analyze |
flutter test |
package.json |
Node/JS/TS | Bash(npm *), Bash(npx *), Bash(node *) |
read scripts.lint | read scripts.test |
go.mod |
Go | Bash(go *) |
go vet, golangci-lint run |
go test ./... |
Cargo.toml |
Rust | Bash(cargo *) |
cargo clippy |
cargo test |
pyproject.toml or requirements.txt |
Python | Bash(python *), Bash(pip *), Bash(pytest *) |
ruff check |
pytest |
composer.json |
PHP | Bash(composer *), Bash(php *) |
phpcs or phpstan |
phpunit |
Gemfile |
Ruby | Bash(bundle *), Bash(ruby *), Bash(rails *) |
rubocop |
rspec or rails test |
*.xcodeproj or Package.swift |
iOS/Swift | Bash(xcodebuild *), Bash(swift *) |
swiftlint |
xcodebuild test |
Makefile |
Generic | Bash(make *) |
make lint |
make test |
Always add Bash(git *) for every stack.
For Node/JS: read package.json scripts to find the REAL command names (lint, test, typecheck, build). NEVER guess.
For Makefile: read actual targets. NEVER assume.
If multiple stacks detected (monorepo): list them and ask confirmation before proceeding.
Run git log --oneline -10 for project context.
Phase 2 — Configure Permissions
Target: .claude/settings.json in the PROJECT directory (NOT ~/.claude/settings.json).
- If
.claude/settings.jsonexists, read existingpermissions.allowarray - Add permissions from the stack table above — do NOT overwrite existing entries
- Merge cleanly: append only new entries
- Show the user what was added
Phase 3 — Git Commit Rules
Generate .claude/git-commit-rules.md:
- Read
git log --oneline -20 - Detect: conventional commits? Language (FR/EN)? Scope prefix? Ticket references?
- If convention detected → formalize it in the rules file
- If no clear convention → propose conventional commits in the project's language
- Present the rules and wait for validation before writing
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.
- 4d ago First seen · 83 lines · 20 tokens per session scan B acd04ec33a4e
setup-project is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 987 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hooks-eval
Evaluate hook security, performance, and SDK compliance. Use for audits.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
review-pr
Perform a comprehensive code review of a pull request.
release-notes-generator
Generate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use for releases, changelogs, version notes, what's new summaries, or ship announcements.
talk-pipeline
Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints for REX or Concept mode talks. Use when starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow.
talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest…