Borrowing it
Nothing to install: this file belongs to nicglazkov/commutescout. 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/nicglazkov/commutescout/main/CLAUDE.mdgit clone --depth 1 https://github.com/nicglazkov/commutescoutWrote 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/nicglazkov/commutescout/claude-md)<a href="https://agentmods.dev/instructions/nicglazkov/commutescout/claude-md"><img src="https://agentmods.dev/badge/instructions/nicglazkov/commutescout/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/nicglazkov/commutescout/claude-md"><img src="https://agentmods.dev/badge/instructions/nicglazkov/commutescout/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 | $0.00373 | $0.00373 |
| Opus 5.5 | $0.00149 | $0.00149 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
commutescout 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
Working on ca-roads-mcp
GCP project pinning (important)
Everything in this repo deploys to GCP project ca-roads-mcp
(15002631928, us-west1). This machine runs multiple agent sessions using
DIFFERENT gcloud projects, and the global gcloud config is shared mutable
state - never rely on it.
- Shells started inside this tree get
CLOUDSDK_CORE_PROJECTandGOOGLE_CLOUD_PROJECTpinned via.envrc(direnv, interactive) and a~/.bashrcpath guard (non-interactive tool shells). - Before any deploy or gcloud mutation, verify:
gcloud config get-value projectmust printca-roads-mcp. - If it does not, prefix the command with the env var or pass
--project ca-roads-mcpexplicitly. Nevergcloud config set project(that mutates the shared global config other sessions depend on).
Ground rules
docs-private/is gitignored and must never be committed, quoted, or referenced in tracked files.- Every change ships as a small PR; merge only after CI is SUCCESS with
no PENDING checks (poll
gh pr checks --json state, never trust piped output alone). - Meaningful changes get a GitHub release (bump
pyproject.tomlandserver.jsontogether); both Cloud Run services redeploy after. - The demo service must run with
--max-instances 1: every rate and cost guard is in-process. - Windows working tree is CRLF after checkout: normalize line endings before string-matching file contents in scripts, or use Read+Edit.
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 · 32 lines · 373 tokens per session scan A c50eed2079a0
commutescout CLAUDE.md is an instructions file published in the GitHub repository nicglazkov/commutescout (5 stars, last pushed 4d ago), licensed MIT. It adds 373 tokens to every session, about $0.0015 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 2026-08-31.
commutescout CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| commutescout CLAUDE.mdnicglazkov/commutescout | Instructions file | 5 | 4d ago | MIT | A | 373 | Claude Code |
| 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 |