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 instructions/poshan0126/dotclaude/claude-mdgit clone --depth 1 https://github.com/poshan0126/dotclaudeWrote 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/instructions/poshan0126/dotclaude/claude-md)<a href="https://agentmods.dev/instructions/poshan0126/dotclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/poshan0126/dotclaude/claude-md.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 5.1 | $0.00449 | $0.00449 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
dotclaude CLAUDE.md 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 6d 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.
What it actually says
dotclaude (this repo)
A Claude Code plugin marketplace: agents, skills, rules, and safety hooks, published from the top-level directories. There is no application code, build, or package manager here — everything is bash + markdown + JSON.
Commands
bash hooks/tests/run-all.sh # run all hook fixture tests (requires jq)
claude plugin validate . --strict # validate marketplace + plugin manifests
Architecture
- Top-level
agents/,skills/,rules/,hooks/are the single source of truth.plugins/<name>/dirs contain only aplugin.jsonplus relative symlinks into the top-level dirs (Claude Code dereferences marketplace-internal symlinks at install) — never put real component copies there. Plugin sources must NOT be"./": with the repo root as plugin root, default component discovery would load every skill/agent into every plugin. CLAUDE.template.mdis the template shipped to user projects by/setupdotclaude. This file (CLAUDE.md) is for working on the repo itself — don't confuse the two.settings.jsonat the repo root is the template users copy to.claude/settings.json; it wires the hooks.
Key decisions
- Versioning: each
plugins/<name>/.claude-plugin/plugin.jsoncarries semver — bump it when that plugin's components change. Marketplace entries carry NO version (plugin.json silently wins; never set both). - Hooks fail open (exit 0) when
jqis missing, except file-protection hooks which fail closed. Hooktimeoutvalues are in seconds. - Agents never set
model— users choose their own.
Workflow
- Every new or modified hook MUST ship with fixtures under
hooks/tests/fixtures/<hook-name>/(see CONTRIBUTING.md). - After changing any manifest, skill, or agent frontmatter, run
claude plugin validate . --strict. - Adding/renaming a skill or agent requires: marketplace entry,
plugins/<name>/(plugin.json + symlink), and the folder README.
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.
- 6d ago First seen · 29 lines · 449 tokens per session scan A 931ff4b24bb9
dotclaude CLAUDE.md is an instructions file published in the GitHub repository poshan0126/dotclaude (860 stars, last pushed 9d ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.