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/microsoft/clarity-agent/agents-mdgit clone --depth 1 https://github.com/microsoft/clarity-agentWhat 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 | $0.02155 | $0.02155 |
| Opus 5 | $0.01077 | $0.01077 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
clarity-agent AGENTS.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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarity Agent Guidelines
Commands
# Install all dependencies
uv sync --all-extras
# Run tests
uv run pytest
# Run a single test file
uv run pytest tests/test_packet_status.py
# Run a single test by name
uv run pytest tests/test_packet_status.py::TestPacketStatus::test_something
# Lint
uv run ruff check .
# Type check
uv run pyright
# Run the web UI (headless, against a project dir)
uv run python clarity.py web /tmp/test-project
# Run the CLI
uv run python clarity.py cli /tmp/test-project
# Run the desktop app
uv run python clarity.py app
# Rebuild the React frontend (only when changing web/ source)
cd web && npm install && npm run build
# Frontend dev server with hot-reloading (proxies /api and /ws to :8420)
# Terminal 1: uv run python clarity.py web /tmp/test-project
# Terminal 2: cd web && npm run dev
Architecture
Mental model: process guides are the program; Python is the stdlib
processes/ contains markdown files that act as the control flow — an LLM reads and executes them. src/clarity_agent/ contains Python infrastructure those processes call. clarity.py is the entry point.
Entry point and routing
processes/clarity-agent.md is "main". It checks whether .clarity-protocol/ exists, runs packet_status.py to assess state, and routes to the correct process guide. After any process completes, control returns here.
src/clarity_agent/protocol/packet_status.py is the build system / flow controller. It maintains a SHA-256 dependency graph among protocol documents (stored in config.json) and detects when a dependency has changed since a document was last accepted. The first stale document in topological order is what to work on next. The --agent flag produces markdown suitable for injection into an AI system prompt.
Document dependency graph
problem → stakeholders → requirements → open-questions → solution → failures
→ architecture (↔ failures)
→ solution-summary (← solution + architecture)
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.
- 2d ago First seen · 137 lines · 2,155 tokens per session scan A b182371ae991
clarity-agent AGENTS.md is an instructions file published in the GitHub repository microsoft/clarity-agent (261 stars, last pushed 12d ago), licensed MIT. It adds 2,155 tokens to every session, about $0.0108 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
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.
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.
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.