Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/generous-corp/pulp/claude-mdgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/claude-md)<a href="https://agentmods.dev/instructions/generous-corp/pulp/claude-md"><img src="https://agentmods.dev/badge/instructions/generous-corp/pulp/claude-md.svg" alt="Measured on agentmods" 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 | $0.32460 | $0.32460 |
| Opus 5 | $0.16230 | $0.16230 |
| Sonnet 5 | $0.06492 | $0.06492 |
| Haiku 4.5 | $0.03246 | $0.03246 |
Grade A, and why
pulp 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 today.
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 — 2,009 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What Is This
Pulp is a cross-platform audio plugin and application framework. MIT-licensed. C++20 core, Swift on Apple, JS-scripted GPU UIs via Dawn/Skia/QuickJS. See VISION.md for the full picture.
Build & Test Commands
Build type — Release is the default
Always build Release unless you're actively investigating a bug. A
Debug build of a JS-scripted GPU UI is dramatically slower than its
Release equivalent (no -O3, no NDEBUG, asserts live, no inlining of
canvas / Skia / Yoga / QuickJS) — slow enough that a UX-perceived
regression in a Debug build is almost always the build type, not the
code. The Codify-Release work made pulp build default to Release;
match that convention when reaching for raw cmake too.
Rules of thumb:
- Default:
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release. Usepulp build(the CLI) when possible — it pins Release for you and refuses to silently flip. - Flip to Debug only when: stepping in a debugger, capturing fresh
runtime::log_infotraces, repro'ing a sanitizer hit, or runningvalidate-build.shfor a clean detached reconfigure pass. Restore Release immediately when the investigation ends. - Reconfigure gotcha: a bare
cmake -S . -B build(no build-type flag) usually preserves the cache value, BUT something in the shipyard / pre-push gate / rebase paths can silently reset the cache to Debug. Pass-DCMAKE_BUILD_TYPE=Releaseevery reconfigure, or usepulp build. - Verify before reporting a build is Release: BOTH
grep '^CMAKE_BUILD_TYPE' build/CMakeCache.txt(should printRelease) ANDgrep '^CXX_FLAGS ' build/<dir>/CMakeFiles/<target>.dir/flags.make(should contain-O3 -DNDEBUG) must check out. Checking only the cache field is necessary-but-not-sufficient — it has been wrong by itself. - A struct-layout change must compile EVERYWHERE before shipping: when a
change alters the field layout of a struct that is brace-initialized
positionally (adding/removing a field, swapping a
boolfor anenum), run a FULLpulp buildover ALL targets — not just the named feature/parity targets — and run it in the background (a full build exceeds a short foreground budget). This is the longest build anyone runs, so it is the one that most needs to take a governed share of the machine rather than every core;pulp build(ortools/ci/governed-build.sh cmake --build build) does that, a rawcmake --build … -j$(sysctl -n hw.ncpu)does not. Stray positional inits in unrelated test files fail closed at compile time, so they are safe, but only a full build surfaces them; building a subset and shipping pushes the discovery to CI. A uniform build failure across macOS/Linux/Windows is the tell for a real compile miss, versus the macOS-only stale-build-dir ODR thepulp-runner-opsskill handles.
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.
- today First seen · 2,009 lines · 32,460 tokens per session scan A aefb2c1aca84
pulp CLAUDE.md is an instructions file published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 32,460 tokens to every session, about $0.1623 per session on Opus 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 2026-09-04.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.