Borrowing it
Nothing to install: this file belongs to vivekchand/clawmetry. 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/vivekchand/clawmetry/main/AGENTS.mdgit clone --depth 1 https://github.com/vivekchand/clawmetryWrote 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/vivekchand/clawmetry/agents-md)<a href="https://agentmods.dev/instructions/vivekchand/clawmetry/agents-md"><img src="https://agentmods.dev/badge/instructions/vivekchand/clawmetry/agents-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/vivekchand/clawmetry/agents-md"><img src="https://agentmods.dev/badge/instructions/vivekchand/clawmetry/agents-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 | $0.01921 | $0.01921 |
| Opus 5.5 | $0.00768 | $0.00768 |
| Sonnet 5.5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
clawmetry 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 4d 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.
AGENTS.md — For AI Coding Agents
Before code: write and review the versioned product record (FLYWHEEL.md section 0c and docs/PRODUCT_RECORDS.md). Requirements and blueprints live in the private clawmetry-cloud records; independent review checks the exact candidate. The requirement is where a change is justified, the blueprint is where it is designed, the code is where it is built -- in that order.
Read
FLYWHEEL.mdfirst. It is how you ship a change end to end in this repo (code → PR → green CI →[RELEASE]→ PyPI → cloud → verified live) and the non-negotiable "done" bar. ThenCLAUDE.mdfor the architecture deep-dive. This file is the short "what to do"; those two carry the detail.
Quick context
ClawMetry is an open-source, real-time observability and governance layer for 32 AI agent runtimes (OpenClaw, NemoClaw, Goose and Qwen Code free in OSS; Claude Code, Codex, Cursor and 25 more with the Pro plugin). The catalogue is entitlements.FREE_RUNTIMES | PAID_RUNTIMES, exported to SUPPORTED_RUNTIMES.txt — the single file every marketing surface and sibling repo reads. Never hardcode the list or the count; regenerate with python3 scripts/sync_runtime_count.py. pip install clawmetry && clawmetry — zero config, observation by default. It's a Flask app with an embedded, no-build vanilla-JS frontend; a sync daemon ingests filesystem/gateway/OTLP data into a local DuckDB store, and the app reads from DuckDB to serve the UI.
Where new code goes (open-core split)
ClawMetry is open-core — there are four repos. Pick the right one before writing code; see FLYWHEEL.md §1b for the full decision tree.
- clawmetry (this repo, public OSS) — the FREE runtime adapters (OpenClaw, NemoClaw, Goose, Qwen Code) + NeMo governance + 24 chat channels + entitlement gate (
clawmetry/entitlements.py) + license client (clawmetry/license.py) + Enterprise feature endpoints (entitlement-gated; impl may defer to clawmetry-pro). Examples:routes/otel_export.py,routes/audit.py. - clawmetry-pro (private; not on public PyPI; shipped via the license-server wheel download) — the 27 gated runtime adapters (Claude Code, Codex, Cursor, …), Pro paid CLI capabilities, advanced-feature implementations. Plugs in via
clawmetry.extensionsentry point. - clawmetry-cloud (private) — cloud SaaS app + license server (
clawmetry-cloud/routes/license.py) + Stripe + admin + closed-wheel hosting (wheels/). - clawmetry-landing (private, public site) — marketing + pricing page + Buy buttons. No gated 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.
- 4d ago Changed · +56 tokens per session 6382620da001
- 1mo ago Changed 7d08a5919ba6
- 1mo ago Changed · +1 lines · +75 tokens per session 784e01a143e7
- 1mo ago Changed · +8 tokens per session a3c07197752c
- 1mo ago Changed 8a9fa938483c
- 1mo ago Changed d48db17787c4
- 1mo ago Changed · +42 tokens per session e414641fb6d9
- 1mo ago Changed · +3 tokens per session df7e5c57482e
- 2mo ago Changed · +129 tokens per session 439c8f115b00
- 2mo ago First seen · 49 lines · 1,608 tokens per session scan A 53279963fd3e
clawmetry AGENTS.md is an instructions file published in the GitHub repository vivekchand/clawmetry (436 stars, last pushed yesterday), licensed MIT. It adds 1,921 tokens to every session, about $0.0077 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 2026-08-30.
clawmetry AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clawmetry AGENTS.mdvivekchand/clawmetry | Instructions file | 436 | yesterday | MIT | A | 1,921 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |