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/metabuilder-labs/tokenjam/claude-mdgit clone --depth 1 https://github.com/Metabuilder-Labs/tokenjamWrote 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/metabuilder-labs/tokenjam/claude-md)<a href="https://agentmods.dev/instructions/metabuilder-labs/tokenjam/claude-md"><img src="https://agentmods.dev/badge/instructions/metabuilder-labs/tokenjam/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 | $0.07850 | $0.07850 |
| Opus 5 | $0.03925 | $0.03925 |
| Sonnet 5 | $0.01570 | $0.01570 |
| Haiku 4.5 | $0.00785 | $0.00785 |
Grade B, and why
tokenjam CLAUDE.md scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
43. **Installed is not resident, and neither gate is visible from the filesystem.** A plugin's skills reach the model only when its key is true in `enabledPlugins` (`~/.claude/settings.json`) AND its install scope in `pl How it starts
The opening of the file, as written. The whole thing — 214 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.
This file is deliberately small. Only what governs every file lives here. Everything else —
architecture detail and path-scoped Critical Rules alike — lives in .claude/rules/*.md, each of
which loads only when you touch a file its paths: frontmatter matches. The single index is at the
bottom of this file — if you are looking for a rule by number, or for an area's architecture notes,
go there first.
Project Overview
tj (TokenJam) is a local-first, OTel-native cost-optimization layer for AI agents (with a full observability stack underneath). No cloud backend, no signup. It captures telemetry from agent runtimes, stores it in a local DuckDB database, and runs the optimize analyzers (the live list is ANALYZER_REGISTRY / ANALYZER_ORDER in tokenjam/core/optimize/runner.py — derive it from there rather than trusting a hand-maintained enumeration) that surface cost-saving candidates from real usage — plus a CLI, local REST API, web UI, and MCP server for querying. Install via pipx install tokenjam (recommended — sidesteps PEP 668 on Homebrew Python and Debian 12+/Ubuntu 24+) or pip install tokenjam in a venv. Run via tj <subcommand>. Requires Python >=3.10.
Build & Development
pip install -e ".[dev]" # dev install
ruff check tokenjam/ # line-length=100, target py310
mypy tokenjam/ # only attr-defined + no-any-return disabled (with justification); see [tool.mypy] in pyproject.toml
# Tests — CI runs all except e2e. Layers: unit = pure logic no I/O <1s; synthetic = span
# injection via factories, zero cost; agents = mock agent scenarios, full SDK path;
# integration = CLI + API. e2e needs TJ_ANTHROPIC_API_KEY and is auto-skipped otherwise.
pytest tests/unit/ tests/synthetic/ tests/agents/ tests/integration/
pytest tests/unit/test_config.py::test_function_name -v # one test
cd sdk-ts && npm install && npm test # TypeScript SDK (independent package)
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.
- 5d ago First seen · 214 lines · 7,850 tokens per session scan B 25f7af1239aa
tokenjam CLAUDE.md is an instructions file published in the GitHub repository Metabuilder-Labs/tokenjam (106 stars, last pushed yesterday), licensed MIT. It adds 7,850 tokens to every session, about $0.0392 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
harness-sdk AGENTS.md
AGENTS.md instructions for strands-agents/harness-sdk, covering agent development guide - strands agents monorepo, context, monorepo layout, where the "why" lives: team/ and writing code.
matryca-plumber AGENTS.md
AGENTS.md instructions for MarcoPorcellato/matryca-plumber, covering agents.md — matryca plumber instruction router, audience map, instruction loading strategy, always-on working agreements and rule and skill routing.
WrenAI AGENTS.md
AGENTS.md instructions for Canner/WrenAI: Repository-wide instructions live in .claude/CLAUDE.md. Please refer to that file for shared build commands, architecture, and conventions.
matryca-plumber CLAUDE.md
Claude Code instructions for MarcoPorcellato/matryca-plumber, covering code audit — code intelligence, always do, never do, resources and cli.
voicegateway CLAUDE.md
Instructions for mahimailabs/voicegateway, covering claude.md, project, commands, install (editable, with dev dependencies) and run tests.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.