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/paiml/pforge/claude-mdgit clone --depth 1 https://github.com/paiml/pforgeWhat 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 | $0.02679 | $0.02679 |
| Opus 5 | $0.01340 | $0.01340 |
| Sonnet 5 | $0.00536 | $0.00536 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
pforge 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 2d 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 — 353 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.
Project Overview
pforge is a zero-boilerplate framework for building Model Context Protocol (MCP) servers through declarative YAML configuration. It's built on pmcp (Pragmatic AI Labs MCP SDK) with strict PMAT quality enforcement.
Design Philosophy: Cargo Lambda simplicity × Flask ergonomics × Rust guarantees
Development Commands
TDD Workflow (Extreme TDD - 5-minute cycles)
# Continuous testing during development
cargo watch -x 'test --lib --quiet' -x 'clippy --quiet'
# Run all tests
cargo test --all
cargo test --all --release
# Fast development cycle
make dev # Runs continuous test + clippy watch
Quality Gates (Required before commit)
# Full quality gate check (run before committing)
make quality-gate
# Individual quality checks
cargo fmt --check # Code formatting
cargo clippy -- -D warnings # Linting
cargo test --all # All tests
cargo tarpaulin --out Json # Code coverage (min 80%)
pmat analyze complexity --max 20 # Cyclomatic complexity
pmat analyze satd --max 0 # Technical debt comments
pmat analyze tdg --min 0.75 # Technical Debt Grade
Testing
# Unit tests (< 1ms each)
cargo test --test unit
# Integration tests (< 100ms each)
cargo test --test integration
# Property-based tests
cargo test --test property --release -- --test-threads=1
# Mutation tests (target: 90%+ mutation kill rate)
cargo mutants --check
Benchmarking
# Run all benchmarks
cargo bench
# Specific benchmark suites
cargo bench --bench dispatch_benchmark
cargo bench --bench throughput_benchmark
# Performance regression check
make bench-check
Building and Running
# Development build
pforge build --debug
# Release build
pforge build --release
# Run server
pforge serve
# Development mode with hot reload
pforge dev --watch
Profiling and Debugging
# Verbose logging
RUST_LOG=pforge=trace pforge serve
# Flamegraph profiling
cargo flamegraph --bin pforge -- serve
# Memory profiling (valgrind)
valgrind --leak-check=full --show-leak-kinds=all target/release/pforge serve
# Heap profiling
cargo run --release --features dhat-heap
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.
- 2d ago First seen · 353 lines · 2,679 tokens per session scan A 74fb646800fc
pforge CLAUDE.md is an instructions file published in the GitHub repository paiml/pforge (3 stars, last pushed 2d ago), licensed MIT. It adds 2,679 tokens to every session, about $0.0134 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 2026-08-31.
Other instructions, from other repositories
mcp AGENTS.md
Instructions for pulseengine/mcp, covering agents.md — rivet project instructions, project overview, available commands, artifact types and working with artifacts.
mcp CLAUDE.md
Instructions for pulseengine/mcp, a project described as: Rust framework for building Model Context Protocol servers and clients. Published to crates.io.
jesse AGENTS.md
Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
playwright-rust CLAUDE.md
Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.