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 Sage-Bionetworks/agent-skills --skill bootstrap-claudemdgit clone --depth 1 https://github.com/Sage-Bionetworks/agent-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/sage-bionetworks/agent-skills/bootstrap-claudemd)<a href="https://agentmods.dev/skills/sage-bionetworks/agent-skills/bootstrap-claudemd"><img src="https://agentmods.dev/badge/skills/sage-bionetworks/agent-skills/bootstrap-claudemd/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/sage-bionetworks/agent-skills/bootstrap-claudemd"><img src="https://agentmods.dev/badge/skills/sage-bionetworks/agent-skills/bootstrap-claudemd.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 | $0.00046 | $0.05049 |
| Opus 5 | $0.00023 | $0.02524 |
| Sonnet 5 | $0.00009 | $0.01010 |
| Haiku 4.5 | $0.00005 | $0.00505 |
Grade A, and why
bootstrap-claudemd 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 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.
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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap CLAUDE.md
Create initial CLAUDE.md files for a repository that has none. Auto-detect the stack, gather ecosystem context, and produce concise files containing only what Claude cannot infer from the code itself.
The user may pass a repo path as an argument, or default to the current working directory.
Core Generation Rules
These rules govern every line written. Violating them produces files that are too long, too vague, or duplicate what tooling already enforces.
- Explore before writing. Read directory structure, manifests, configs, README, and source samples. Never guess or invent details.
- Don't restate tooling. If a convention is enforced by a linter, formatter, or type checker config in the repo, leave it out.
- Only verified commands. Copy commands verbatim from package.json scripts, Makefile, justfile, README, or CI config. Mark inferred commands with
# inferred. - Every constraint needs a reason. "Never do X — because Y." Without a reason, Claude follows the rule in obvious cases and misses edge cases.
- No secrets. Env var names are fine; values, tokens, and connection strings are not.
- Be specific or say nothing. Name exact paths, tools, patterns. Vague guidance produces vague results.
- Keep files concise but complete. Every line must change how Claude behaves. Cut anything inferable from the codebase, anything restating the README, any empty section headers. But do NOT sacrifice coverage for brevity — a thorough 200-line file is better than a thin 50-line file that misses critical patterns.
- Imperative voice. "Use named exports" not "We tend to prefer named exports."
- Focus on non-obvious. Surface what Claude cannot infer from code alone: unusual tooling, generated files that must not be edited, non-standard layouts, monorepo conventions, gotchas.
- Quality test for every line: "If I remove this, will Claude mess up?" No -> delete it. Yes -> keep it.
- Document data models and their flow. Identify key input/output data shapes (JSON schemas, API types, database structures, dbt models, Terraform state, protobuf, CSV/Parquet schemas). Document: where defined, how they flow through the system, non-obvious shape constraints, what generates or consumes them. Critical when data shapes cross module or repo boundaries.
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 · 331 lines · 46 tokens per session scan A 0350109b62a4
bootstrap-claudemd is a skill published in the GitHub repository Sage-Bionetworks/agent-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 5,049 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…