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/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.
<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>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 | $0.01359 | $0.01359 |
| Opus 5.5 | $0.00544 | $0.00544 |
| Sonnet 5.5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
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.
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.rsandsrc/bin/trammel_mcp.rsare the two binaries. Both callsrc/cli.rsandsrc/tools.rs.src/planner.rs,src/score.rs,src/strategies.rs,src/implicit.rsdecompose a goal and run the nine beams. Implicit-edge rules aredata/patterns.json, embedded withinclude_str!.src/lang/detects language, extracts symbols, and resolves imports. Python uses the stele-context parser undersrc/syntax/,src/lang/python/, andsrc/lang/python_symbols/.scripts/syntax_core_manifest.txtis their digest. Other languages usesrc/lang/code.rs,src/lang/symbols.rs, andsrc/lang/imports.rs.src/store.rsis the.trammel/storesnapshot.src/migrate.rsreads an oldtrammel.dband its WAL, read-only.schemas/has one result schema per tool. A new tool needs a schema file, a row insrc/tools.rs, an entry insrc/catalogue.rs(description and input schema fortools/list), and a group insrc/groups.rs.tests/archetypes/andparity/fixtures/are sample projects for the Rust tests. They are not a Python package.tests/goldens/test_farm_decompose.jsonis 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.
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.
- yesterday Changed · +2 lines · +343 tokens per session 9289646289c5
- 2d ago Changed · +3 lines · -454 tokens per session 64d8e276f711
- 2mo 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 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.
Trammel CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Trammel CLAUDE.mdIronAdamant/Trammel | Instructions file | 1 | yesterday | MIT | A | 1,359 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |