Trammel: Instructions file for Claude Code

CLAUDE.md

Trammel CLAUDE.md is an instructions file for Claude Code from IronAdamant/Trammel. It costs 1,359 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 AGENTS.md.

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/github.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/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.

agentmods 80×15 button for Trammel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ironadamant/trammel/claude-md"><img src="https://agentmods.dev/badge/instructions/ironadamant/trammel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,359 This file is loaded in full into every session.
When invoked 1,359 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 $0.01359 $0.01359
Opus 5.5 $0.00544 $0.00544
Sonnet 5.5 $0.00272 $0.00272
Haiku 4.5 $0.00136 $0.00136

Measured yesterday against content hash 9289646289c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 yesterday.

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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Trammel 4.x is one std-only Rust binary (trammel, trammel-mcp) plus the npm wrapper @iron_adamant/trammel. npx -y @iron_adamant/trammel mcp starts the MCP server. The old Python version lives on the python-legacy branch.

This file is the source-tree guide. Do not confuse it with a client CLAUDE.md that tells an assistant how to call the MCP server.

Commands

cargo test --locked
cargo build --release
cargo run --example check_zero_deps
cargo run --example check_no_todos
cargo run --example check_syntax_core
cargo run --release --example bench_gate -- --self-test
cargo run --release --example bench_gate -- target/release/trammel

The repo checks are std-only Rust in examples/ (the Python scripts they replace are on python-legacy). cargo test runs their unit tests. Run them from the repo root.

trammel doctor is JSON by default. --human prints indented JSON. --version prints {"version":"<Cargo.toml version>",...}. To release X.Y.Z, edit only the manifests: Cargo.toml, Cargo.lock, every npm/*/package.json (wrapper optionalDependencies too), and server.json. tests/npm_packages.rs checks they agree with CARGO_PKG_VERSION.

scripts/release.sh X.Y.Z checks Cargo.toml and prints the tag command. It does not tag or publish.

Layout

  • src/ is the library. src/main.rs and src/bin/trammel_mcp.rs are the two binaries. Both call src/cli.rs and src/tools.rs.
  • src/planner.rs, src/score.rs, src/strategies.rs, src/implicit.rs decompose a goal and run the nine beams. Implicit-edge rules are data/patterns.json, embedded with include_str!.
  • src/lang/ detects language, extracts symbols, and resolves imports. Python uses the stele-context parser under src/syntax/, src/lang/python/, and src/lang/python_symbols/. scripts/syntax_core_manifest.txt is their digest. Other languages use src/lang/code.rs, src/lang/symbols.rs, and src/lang/imports.rs.
  • src/store.rs is the .trammel/store snapshot. src/migrate.rs reads an old trammel.db and its WAL, read-only.
  • schemas/ has one result schema per tool. A new tool needs a schema file, a row in src/tools.rs, an entry in src/catalogue.rs (description and input schema for tools/list), and a group in src/groups.rs.
  • tests/archetypes/ and parity/fixtures/ are sample projects for the Rust tests. They are not a Python package.
  • tests/goldens/test_farm_decompose.json is the decompose golden. bench/ holds recorded timings.
  • npm/ is the wrapper and the six platform packages. The release workflow copies binaries in at publish time.

Read the full file on GitHub · 62 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. yesterday Changed · +2 lines · +343 tokens per session 9289646289c5
  2. 2d ago Changed · +3 lines · -454 tokens per session 64d8e276f711
  3. 2mo 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 yesterday), licensed MIT. It adds 1,359 tokens to every session, about $0.0054 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 2026-08-31.

Related

Trammel CLAUDE.md compared with instructions from other repositories

Trammel CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Trammel CLAUDE.mdIronAdamant/TrammelInstructions file1yesterdayMITA1,359Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode