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 toBzh30/Claude-Project-Bootstrap --skill bootstrap-working-agreementsgit clone --depth 1 https://github.com/toBzh30/Claude-Project-BootstrapWrote 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/tobzh30/claude-project-bootstrap/bootstrap-working-agreements)<a href="https://agentmods.dev/skills/tobzh30/claude-project-bootstrap/bootstrap-working-agreements"><img src="https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/bootstrap-working-agreements/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/tobzh30/claude-project-bootstrap/bootstrap-working-agreements"><img src="https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/bootstrap-working-agreements.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 | $0.00098 | $0.06960 |
| Opus 5 | $0.00049 | $0.03480 |
| Sonnet 5 | $0.00020 | $0.01392 |
| Haiku 4.5 | $0.00010 | $0.00696 |
Grade B, and why
bootstrap-working-agreements scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -nE '^\.claude/?$' .gitignore 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bootstrap-working-agreements — One-shot project setup
The goal: in one pass on a fresh (or fresh-to-tooling) repo, lay down everything that makes future Claude sessions productive — GitHub Project, working agreements, roadmap, CLAUDE.md hub + spokes — with project-specific values substituted in (not generic placeholders left for the user to fill in later).
This skill proposes and waits for confirmation before writing anything. Almost every value is project-specific.
Step 0 — Working tree check
This skill writes multiple files (.claude/rules/working-agreements.md, root CLAUDE.md, optional spokes) and calls into github-project-setup (which writes more). Before any changes, give the user a clean baseline to git diff against if something goes wrong:
git status --short
If the output is non-empty, halt and report:
Uncommitted changes in
<N>files:<git status --short output, truncated to 10 lines if longer>This skill writes several new and modified files across the repo. If anything goes wrong you'll want a clean baseline. Commit/stash first, or continue anyway?
Wait for explicit "continue" before proceeding. Don't proceed silently.
If git status --short errors (not a git repo), warn the user and ask whether to proceed without a revert baseline. Recommend git init first.
Step 0.5 — Check .gitignore for .claude/ patterns
This skill commits three things under .claude/: durable rules in .claude/rules/, the plugin-enablement file .claude/settings.json (Step 6.5), and — via github-project-setup — .claude/gh-project.json. A directory-level ignore (.claude/ with a trailing slash) silently excludes all of them — git can't re-include children of a fully-excluded directory, so they won't show up in git status until someone notices.
grep -nE '^\.claude/?$' .gitignore 2>/dev/null
If a .claude/ line is found, propose the carve-out fix — replace it with:
.claude/*
!.claude/rules/
!.claude/settings.json
!.claude/gh-project.json
What ships with it
4 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.
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.
- 9d ago First seen · 430 lines · 98 tokens per session scan B e1a1335850b2
bootstrap-working-agreements is a skill published in the GitHub repository toBzh30/Claude-Project-Bootstrap (3 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 6,960 once invoked, about $0.0005 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
issue-train
Batch-process every open GitHub issue in a list — triage, detect existing PR linkage, detect silent fixes in already-merged PRs, close issues that are no longer pertinent, then plan + build + open one PR per remaining actionable issue with Closes.
merge-train
Batch-process a list of open GitHub pull requests. From a GitHub PRs URL (or the current repo), enumerate every open PR, compute the safe merge order from dependencies, then per PR fix CI, resolve merge conflicts, run a code review, and assign a status (mergeable / changes-required / blocked-by-order). Presents one…
{{project_slug}}-ticket
End-to-end local automation for a single Jira ticket on the {{projectdisplayname}} repo. Paste a Jira ticket URL (or key) and the skill self-assigns the ticket, reads it, refines it, creates the Jira sub-tasks, branches off the integration branch in an isolated git worktree, implements the work in parallel via…
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.