Borrowing it
Nothing to install: this file belongs to specsnl/agent-specs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/specsnl/agent-specs/main/CLAUDE.mdgit clone --depth 1 https://github.com/specsnl/agent-specsWrote 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/specsnl/agent-specs/claude-md)<a href="https://agentmods.dev/instructions/specsnl/agent-specs/claude-md"><img src="https://agentmods.dev/badge/instructions/specsnl/agent-specs/claude-md/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/instructions/specsnl/agent-specs/claude-md"><img src="https://agentmods.dev/badge/instructions/specsnl/agent-specs/claude-md.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 | $0.00449 | $0.00449 |
| Opus 5.5 | $0.00180 | $0.00180 |
| Sonnet 5.5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
agent-specs 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 2mo 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
agent-specs
This repo is a Claude Code plugin marketplace. Each plugin under plugins/<name>/
bundles some combination of skills, commands, MCP servers, hooks, and agents.
Keep plugin READMEs in sync
Every plugin's README.md must accurately list all the elements the plugin
currently contains — skills, commands, MCP servers, hooks, agents, or anything
else it ships. Whenever you add, remove, or rename any of these inside a
plugin (e.g. a new skill directory under plugins/<name>/skills/, a new
command under plugins/<name>/commands/, a hook, an MCP server, an agent),
update that plugin's README.md in the same change so it never drifts from
what's actually in the plugin directory.
Keep the root README in sync
The root README.md plugins table must list every plugin declared in
.claude-plugin/marketplace.json. Whenever a plugin is added, removed, or
renamed in the marketplace manifest, update the root README.md table to
match.
Keep plugin descriptions in sync
Each plugin declares its description in two places: its own
plugin.json (or .claude-plugin/plugin.json) and its entry in the root
.claude-plugin/marketplace.json. The CLI reads the description from
marketplace.json, so both must always carry the same text. Whenever you
change a plugin's description, update it in both files.
Formatting tables
After editing any markdown table in this repo, use the
code:autofix-markdown-tables skill to keep columns properly padded and
aligned. It runs this repo's md:fix-tables task.
Markdown linting
Every .md file is linted with markdownlint-cli2 (config in
.markdownlint-cli2.yaml), and the Markdown workflow enforces it in CI.
After editing markdown, run:
task md:checkstyle # lint only
task md:fixstyle # align tables, then apply autofixable lint rules
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.
- 2mo ago Changed · +11 lines · +97 tokens per session 77a7c2058201
- 2mo ago First seen · 36 lines · 352 tokens per session scan A 8661185d9d3a
agent-specs CLAUDE.md is an instructions file published in the GitHub repository specsnl/agent-specs (2 stars, last pushed 1mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0018 per session on Opus 5.5. 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.
agent-specs CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-specs CLAUDE.mdspecsnl/agent-specs | Instructions file | 2 | 1mo ago | MIT | A | 449 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |