Borrowing it
Nothing to install: this file belongs to IronAdamant/Trammel. 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/IronAdamant/Trammel/main/CLAUDE.mdgit clone --depth 1 https://github.com/IronAdamant/TrammelWrote 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/ironadamant/trammel/claude-md)<a href="https://agentmods.dev/instructions/ironadamant/trammel/claude-md"><img src="https://agentmods.dev/badge/instructions/ironadamant/trammel/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 5.1 | $0.01470 | $0.01470 |
| Opus 5 | $0.00735 | $0.00735 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
Trammel 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 8d 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 — 57 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 This Is
Trammel is a dependency-aware task planner for LLM coding assistants: it decomposes goals into ordered steps, explores strategy variants (beam search), verifies steps, learns constraints from failures, and stores successful strategies as reusable recipes. It ships as a Python library, a CLI, and an MCP server (33 tools; ~12 primary advertised by default via TRAMMEL_MCP_SURFACE).
Note: the global ~/CLAUDE.md describes how to use the Trammel MCP server as a client. This repo is Trammel's source — don't confuse the two when "trammel" tools appear in your MCP tool list.
Hard constraint: the core is stdlib-only. Do not add third-party dependencies. The only dependency is the optional mcp package (extra: trammel[mcp]) used by the MCP server entry point.
Commands
pip install -e '.[mcp]' # dev install
# Tests (unittest, same command CI runs on Python 3.10–3.13)
python -m unittest discover -v -s tests -p 'test_*.py' # full suite
python -m unittest tests.test_strategies -v # one module
python -m unittest tests.test_trammel.SomeCase.test_name # one test
pytest # also configured (pyproject excludes tests/archetypes)
# Run
python -m trammel "some goal" --root /path/to/project --dry-run # CLI (explore only)
trammel-mcp # MCP server on stdio; TRAMMEL_DB_PATH overrides db location
Releases: bump version in pyproject.toml (see scripts/release.sh); publishing to PyPI happens via GitHub release → publish.yml (OIDC trusted publishing, no tokens).
Architecture
All state lives in one SQLite database (DEFAULT_DB_PATH = "trammel.db", relative to cwd; *.db is gitignored). Layers, top to bottom:
MCP layer — mcp_stdio.py (entry point) → dispatch_tool() in mcp_server.py → per-tool _handle_* functions. Tool JSON schemas live in tool_schemas.py. The two registries (_TOOL_SCHEMAS, _DISPATCH) are diffed at module import and a mismatch raises RuntimeError — to add an MCP tool you must touch both files, then add a smoke test in tests/test_mcp_dispatch.py (which also asserts parity). coerce_int_params() casts string→int per schema because MCP clients may stringify numbers.
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.
- 8d ago First seen · 57 lines · 1,470 tokens per session scan A 51e43c7f5b2b
Trammel CLAUDE.md is an instructions file published in the GitHub repository IronAdamant/Trammel (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,470 tokens to every session, about $0.0073 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
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.
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 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).
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.
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.