Borrowing it
Nothing to install: this file belongs to algorismo-au/lanekeep. 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/algorismo-au/lanekeep/main/CLAUDE.mdgit clone --depth 1 https://github.com/algorismo-au/lanekeepWrote 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/algorismo-au/lanekeep/claude-md)<a href="https://agentmods.dev/instructions/algorismo-au/lanekeep/claude-md"><img src="https://agentmods.dev/badge/instructions/algorismo-au/lanekeep/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/algorismo-au/lanekeep/claude-md"><img src="https://agentmods.dev/badge/instructions/algorismo-au/lanekeep/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 | $0.01255 | $0.01255 |
| Opus 5.5 | $0.00502 | $0.00502 |
| Sonnet 5.5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
lanekeep 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 10d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaneKeep — Developer Guide
Operating protocol: see .claude/AGENT_OPERATING_PROTOCOL.md — read first, always.
What This Is
LaneKeep is a governance guardrails and insights tool for AI coding agents (Claude Code). It intercepts tool calls via Claude Code's PreToolUse hook, evaluates them through a tiered pipeline, and enforces allow/deny decisions. Disabled by default — opt-in.
Table of Contents
Project Layout
lanekeep/
bin/ CLI entry points (20 executables: lanekeep, lanekeep-serve,
lanekeep-handler, lanekeep-trace, lanekeep-audit, lanekeep-rules,
lanekeep-policy, lanekeep-scan, lanekeep-parse-spec, etc.)
lib/ Evaluator modules and shared libraries
hooks/ Claude Code hook scripts (evaluate.sh, post-evaluate.sh,
stop.sh, auto-format.sh, cursor-eval.sh, cursor-post-eval.sh)
defaults/ Default config (lanekeep.json)
ui/ Web dashboard (index.html + server.py)
vendor/ Vendored JS libs (DOMPurify, Mermaid)
tests/ Bats tests and fixtures (organized by category)
config/ Config loading, integrity, layering, schema
evaluators/ Hardblock, codediff, result-transform
rules/ Rule patterns, custom rules, CLI, update, signing
plugins/ Plugin commands, decisions, polyglot, webhook
hooks/ Hook protocol, post-handler, stop, init
pipeline/ Handler, dispatcher, concurrency, session boundary
observability/ Trace, trace-clear, insights metrics
ui/ Server API tests (Python)
cli/ CLI commands, PRP parser
fixtures/ JSON test fixtures, sample PRPs
plugins.d/ Plugin evaluators (subshell isolated)
examples/ Example plugins
Core Concepts
| Term | What it is |
|---|---|
| Event | A raw tool call occurrence — one record per hook fire (PreToolUse or PostToolUse). total_events always increments regardless of outcome. |
| Evaluation | An individual check within the pipeline. Each evaluator module (eval-hardblock.sh, eval-rules.sh, eval-budget.sh, etc.) independently examines the event and sets EVAL_PASSED/EVAL_REASON. A single event triggers many evaluations; results recorded in the trace evaluators[] array with name, tier, and passed. |
| Decision | The final pipeline verdict: allow, deny, warn, or ask. Stored in the decision field of each trace entry and counted in decisions.deny / warn / ask / allow in cumulative metrics. |
| Action | An event where the tool actually ran (allow or warn). Denied and pending-ask calls don't count. eval-budget.sh increments action_count only when already_blocked != true and skip_increment != true — this is what budget.max_actions measures. |
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.
- 10d ago Changed · -50 tokens per session 1ee0af5aefac
- 25d ago Changed · +4 lines · +109 tokens per session 6aa59fd4846e
- 1mo ago First seen · 94 lines · 1,196 tokens per session scan A ab5dc4536a71
lanekeep CLAUDE.md is an instructions file published in the GitHub repository algorismo-au/lanekeep (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,255 tokens to every session, about $0.0050 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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.