Borrowing it
Nothing to install: this file belongs to heikki-laitala/pruner. 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/heikki-laitala/pruner/main/CLAUDE.mdgit clone --depth 1 https://github.com/heikki-laitala/prunerWrote 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/heikki-laitala/pruner/claude-md)<a href="https://agentmods.dev/instructions/heikki-laitala/pruner/claude-md"><img src="https://agentmods.dev/badge/instructions/heikki-laitala/pruner/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/heikki-laitala/pruner/claude-md"><img src="https://agentmods.dev/badge/instructions/heikki-laitala/pruner/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 | $0.00608 | $0.00608 |
| Opus 5.5 | $0.00243 | $0.00243 |
| Sonnet 5.5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
pruner 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pruner
Pre-computed code context engine for AI coding agents. Tree-sitter call graphs + keyword matching, no LLM. Injects relevant files, symbols, and execution paths via Claude Code hook.
Engineering Principles
KISS
Prefer straightforward control flow. Keep error paths obvious and localized.
YAGNI
Do not add interfaces, config keys, or abstractions without a concrete caller. No speculative features.
DRY (Rule of Three)
Duplicate small local logic when it preserves clarity. Extract shared helpers only after three repeated, stable patterns.
TDD
Write tests first. Red → Green → Refactor. New features and bug fixes start with a failing test that defines the expected behavior before writing implementation code.
Secure by Default
Never log secrets or tokens. Validate at system boundaries. Keep network/filesystem/shell scope narrow.
Validating Changes
When changing scoring, ranking, context output, or anything that affects pruner's suggestions:
-
Posthoc analysis first (~5 seconds, no API calls):
cargo build --release python3 tests/posthoc_analysis.py tests/ab-tests/sonnet_nest_oneshot_n10_v027_20260406.json --repo /tmp/pruner-bench/nest --pruner ./target/release/prunerCheck: did recall improve? Did precision change? Which files are still missed?
-
Fast A/B test if posthoc looks good (~15-20 min, ~$1-2):
python3 tests/ab_test.py --fast --task implement --rounds 5 --save-raw --validate-cacheCheck: did cost/tools/time improve in real Claude sessions?
-
Full A/B test for final validation (~45 min, ~$5):
python3 tests/ab_test.py --save-raw --validate-cache
Step 1 replaces a 20+ min A/B test with a 5-second offline check. Only proceed to step 2 when posthoc shows improvement. Step 3 is for release validation only.
The test repos need to be cloned first (the A/B test harness does this automatically, or manually: git clone https://github.com/nestjs/nest.git /tmp/pruner-bench/nest).
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.
- 1mo ago First seen · 70 lines · 608 tokens per session scan A 817d03c19f42
pruner CLAUDE.md is an instructions file published in the GitHub repository heikki-laitala/pruner (16 stars, last pushed 4mo ago), licensed MIT. It adds 608 tokens to every session, about $0.0024 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 2026-09-26.
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.