Borrowing it
Nothing to install: this file belongs to fellowship-dev/navvi. 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/fellowship-dev/navvi/main/CLAUDE.mdgit clone --depth 1 https://github.com/fellowship-dev/navviWrote 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/fellowship-dev/navvi/claude-md)<a href="https://agentmods.dev/instructions/fellowship-dev/navvi/claude-md"><img src="https://agentmods.dev/badge/instructions/fellowship-dev/navvi/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/fellowship-dev/navvi/claude-md"><img src="https://agentmods.dev/badge/instructions/fellowship-dev/navvi/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 | $0.00615 | $0.00615 |
| Opus 5.5 | $0.00246 | $0.00246 |
| Sonnet 5.5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
navvi 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 18d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Navvi v3
Self-healing scraper compiler. The current plan lives in
fellowship-dev/claude-buddy under
specs/plans/2026-09-22-007-navvi-prompt-to-scraper.md — brief to spec to
investigation to scraper, with the original compiler plan
(specs/plans/2026-09-19-001-feat-jev-compiled-scraper-actor-plan.md) behind
it, and specs/plans/2026-09-22-008-navvi-remaining-phases.md after it — the
driver (navvi make, src/make/), sample, determinism, and the live run
that found three seam defects no unit test could see. That plan's two
transcripts under "The flow" are tests/make.test.ts's specification,
exactly as written.
Verify
npm run typecheck,npm run typecheck:testsandnpm teston every change. Tests are offline: recorded chooser answers, fixtures served from disk.npm run typecheckreadstsconfig.json, which excludestests/; vitest only strips test types.npm run typecheck:tests(tsconfig.test.json, same strictness) is the only command that checks them, so a change undertests/is not verified without it.npm run demoruns the two-version pharmacy proof offline.npm run test:liveneeds a key and is required after changes undersrc/chooser,src/compile,src/navigate,src/replay/heal.ts,src/secretsorsrc/browser/policy.ts.
Rules
playwrightstays pinned to 1.60.0 (the Apify Dockerfiles and.devcontainer/follow it;scripts/check-image-pins.mjschecks):camoufox-jscapsplaywright-corebelow 1.61 and the Apify Camoufox image tops out at 1.60.0.- Secrets are
{{secret:name}}placeholders filled by code. A secret value never enters a chooser question, a log, a trace or the scraper JSON. - The chooser only picks among code-enumerated options. Never let model output become a selector or a script.
storage/holds browser profiles with live sessions. Never commit it, never copy it between machines.- A heuristic ships with its fixture in the same commit
(
src/heuristics/,tests/fixtures/heuristics/). A rule with no eval is prose, and prose does not execute: every finding of 2026-09-22 was already written down in a plan document and was rediscovered anyway.
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.
- 18d ago Changed · +25 tokens per session 6a8851cdb790
- 25d ago Changed · +5 lines · +94 tokens per session 97fdd18b19e6
- 26d ago Changed · +12 lines · +200 tokens per session 46ea82b164b1
- 29d ago First seen · 25 lines · 296 tokens per session scan A a49a082bb7b2
navvi CLAUDE.md is an instructions file published in the GitHub repository fellowship-dev/navvi (10 stars, last pushed 18d ago), licensed MIT. It adds 615 tokens to every session, about $0.0025 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 2026-09-20.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.