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/danielrmay/claudity/claude-mdgit clone --depth 1 https://github.com/danielrmay/claudityWhat 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 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
claudity 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudity — contributor context
Claude Code plugin port of Microsoft's Clarity Agent. Most files here are VENDORED from microsoft/clarity-agent under a strict porting contract — read the contract before editing anything:
- PORTING.md — substitution rules; every deviation in a vendored file must trace to a rule
- UPSTREAM.md — pin, vendoring map, re-sync and release procedure
- TESTING.md — the tiered harness and what each tier proves
- CONTRIBUTING.md — upstream-first policy, adding thinkers
Invariants
- Vendored files: after touching anything in the upstream.json watch set,
run
python3 scripts/upstream_audit.py— unexplained changed lines fail CI. Vendored headers carry the pin; pin-consistency tests fail until headers, upstream.json, and UPSTREAM.md agree. - Zero dependencies: python3 stdlib only, nothing pip-installed — including the MCP server (hand-rolled stdio JSON-RPC; "Transport" note in PORTING.md).
- Windows portability: all file I/O passes
encoding="utf-8"(the locale default corrupts unicode markdown) and path comparisons in tests useas_posix(). The windows-latest CI job enforces both under cp1252 — never set PYTHONUTF8 in CI; it masks exactly these bugs. The e2e harness is POSIX-only (its tests skip on win32). - Versioning: bump
.claude-plugin/plugin.jsonand.claude-plugin/marketplace.jsontogether (test-enforced). Releases viaclaude plugin tag.
Testing
- Tier 1 (free, run always):
.venv/bin/python -m pytest tests/ -qplus the audit above. Tier 0:claude plugin validate .. - Tier 2 (paid, local):
tests/e2e/run.sh— see TESTING.md for model floors and stress mode. Sessions run against a frozen, hash-verified snapshot of the plugin, never this repo — plugin-content edits during a background run are safe, but don't edit the harness scripts (tests/e2e/) mid-run. - If the post-run repo-dirty warning ever fires, the snapshot indirection leaked — investigate, don't shrug.
scripts/mcp_server.pyedits need a session restart (or/reload-plugins) interactively; pytest spawns fresh server processes, so tests always see current code.
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.
- 3d ago First seen · 50 lines · 642 tokens per session scan A 01640edbc9e2
claudity CLAUDE.md is an instructions file published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 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 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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.