Borrowing it
Nothing to install: this file belongs to lambdalisue/cclens. 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/lambdalisue/cclens/main/AGENTS.mdgit clone --depth 1 https://github.com/lambdalisue/cclensWrote 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/lambdalisue/cclens/agents-md)<a href="https://agentmods.dev/instructions/lambdalisue/cclens/agents-md"><img src="https://agentmods.dev/badge/instructions/lambdalisue/cclens/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/lambdalisue/cclens/agents-md"><img src="https://agentmods.dev/badge/instructions/lambdalisue/cclens/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 | $0.00713 | $0.00713 |
| Opus 5.5 | $0.00285 | $0.00285 |
| Sonnet 5.5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
cclens 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 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cclens
A CLI that analyzes Claude Code usage to show where your Claude Code
configuration can be optimized, and how. It measures the cost (context
tokens, wall-clock time, friction) and actual usage of every configuration
surface — skills, rules, hooks, MCP servers and their tool schemas, agents,
CLAUDE.md / AGENTS.md / memory, permissions — and surfaces the optimization
wedges: high cost with low use (prune), always-on cost used only rarely
(defer/split), redundancy (merge), recurring friction (configure).
Skills are just one surface among many; the tool is configuration-wide.
AI-assisted optimization proposals are a planned future layer on top of this analysis core — the core's job is to measure and visualize, not to advise.
How it is built
This project is spec-driven and test-driven.
- Spec first.
docs/specs/holds the design intent (the why and the contract), split by concern. Read the owning spec before changing behavior; update it in the same change. See.claude/rules/spec-sync.md. - Test first. Red → green → refactor, t-wada style. Keep the analysis core
(records → events → aggregation) pure and I/O-free so it is unit-testable
against small synthetic fixtures. See
.claude/rules/tdd.md. - Privacy is a hard constraint. Real transcripts and real config can contain
personal data and secrets. Test fixtures are synthetic; harvested transcripts,
captured config, and generated databases are never committed. See
.claude/rules/session-data-privacy.md.
Architecture
Two stages, decoupled by an intermediate SQLite store:
transcripts + config ──analyze──▶ SQLite (sessions · surfaces · events) ──▶ consumers
analyze reads two kinds of Claude Code input — session transcripts (what
was actually used and at what cost) and live config (what is installed and
its static cost) — and writes a normalized store. The first consumer is CLI
reporting (tables / Markdown); a later consumer feeds the same store to AI for
optimization proposals, a surface left undesigned until decided. The store
exists so every consumer reads pre-computed data instead of re-parsing the
input. Implementation language is Rust; the store is SQLite.
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 First seen · 60 lines · 713 tokens per session scan A 0fc802ce33de
cclens AGENTS.md is an instructions file published in the GitHub repository lambdalisue/cclens (141 stars, last pushed 13d ago), licensed MIT. It adds 713 tokens to every session, about $0.0029 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.
cclens AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cclens AGENTS.mdlambdalisue/cclens | Instructions file | 141 | 13d ago | MIT | A | 713 | 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 |