Trammel: Instructions file for Claude Code

CLAUDE.md

Trammel CLAUDE.md is an instructions file for Claude Code from IronAdamant/Trammel. It costs 1,470 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Trammel, a task planner for AI coding assistants that breaks goals into ordered steps and checks the results.

In plain words
What is it for?
They are for explaining Trammel's architecture and development workflow, including its Python test command and dependency rules.
Why use it?
They give a coding assistant the project context, constraints, installation commands, and test commands needed to work safely in that repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is IronAdamant/Trammel's own configuration. It tells Claude Code how to work on Trammel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Trammel configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/IronAdamant/Trammel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/IronAdamant/Trammel

Made for: Claude Code.

Wrote 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.

agentmods badge for Trammel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ironadamant/trammel/claude-md.svg)](https://agentmods.dev/instructions/ironadamant/trammel/claude-md)
Your own site
<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>
Per session 1,470 This file is loaded in full into every session.
When invoked 1,470 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 51e43c7f5b2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

CLAUDE.md · 57 lines

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 layermcp_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 RuntimeErrorto 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.

Read the full file on GitHub · 57 lines

Changes

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.

  1. 8d ago First seen · 57 lines · 1,470 tokens per session scan A 51e43c7f5b2b

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens