agentmods.dev

tokenjam AGENTS.md

Repository instructions for coding agents that explains which project guide to follow and lists essential rules for storage, configuration, architecture, tracing, output, and tests.

In plain words
What is it for?
Use it when an agent works on the TokenJam codebase and needs the project's current development rules.
Why use it?
It prevents agents from using the wrong database, file format, imports, tracing setup, or test helpers.

Instructions file for CodexOpenCode

106 5d ago A scan 260 tokens original MIT
View the source file Metabuilder-Labs/tokenjam
Install

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.

agentmods
npx agentmods add instructions/metabuilder-labs/tokenjam/agents-md
Clone the repo
git clone --depth 1 https://github.com/Metabuilder-Labs/tokenjam

Made for: Codex, OpenCode.

Per session 260 This file is loaded in full into every session.
When invoked 260 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00260 $0.00260
Opus 5 $0.00130 $0.00130
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 3d ago against content hash 1c6e25239659, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokenjam AGENTS.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 3d 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.

AGENTS.md · 17 lines

What it actually says

AGENTS.md — TokenJam

AI coding agents working in this repo should read CLAUDE.md instead. CLAUDE.md is the maintained source of truth and is kept up to date by the agents working in this codebase. This file exists only for tools that look specifically for AGENTS.md (Codex, Gemini Code, etc.).

Quick rules for agents that don't read CLAUDE.md

  1. Storage is DuckDB — never import sqlite3, never write SQLite queries
  2. Config is TOML — tomllib.load() requires open(path, "rb") binary mode
  3. tokenjam/core/ has no CLI or HTTP imports — pure domain logic only
  4. @watch() alone does not create LLM spans — requires patch_anthropic() etc.
  5. Never use unicode bullet characters in output — Rich handles formatting
  6. Tests use InMemoryBackend and tests/factories.py — never construct NormalizedSpan directly

Read CLAUDE.md for the full architecture, development guide, and current rules.

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. 3d ago First seen · 17 lines · 260 tokens per session scan A 1c6e25239659

Subscribe to this mod's changes

tokenjam AGENTS.md is an instructions file published in the GitHub repository Metabuilder-Labs/tokenjam (106 stars, last pushed 5d ago), licensed MIT. It adds 260 tokens to every session, about $0.0013 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 2026-08-30.

Autonomous AgentsLLMai-agentscliduckdbobservability
Related

Other instructions, from other repositories

ai-observer CLAUDE.md

Instructions for tobilg/ai-observer, covering claude.md, project overview, build & development commands, setup and development.

tobilg/ai-observer · 3,189 tokens

Financial-API AGENTS.md

Instructions for HiThink-Tech/Financial-API, covering agents.md, 必读顺序, monorepo 边界, 选择接入方式 and api key.

HiThink-Tech/Financial-API · 1,319 tokens

openstatus AGENTS.md

AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.

openstatusHQ/openstatus · 1,308 tokens

OwnPilot AGENTS.md

Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.

ownpilot/OwnPilot · 1,260 tokens

agentic-os AGENTS.md

Instructions for modimihir07/agentic-os, covering agentic os — complete project context for ai agents, role definition, project identity, architecture and 3-agent engine.

modimihir07/agentic-os · 5,932 tokens

zeroshot AGENTS.md

AGENTS.md instructions for the-open-engine/zeroshot, covering zeroshot: multi-agent coordination engine, critical rules, where to look, cluster worker contracts and cli quick reference.

the-open-engine/zeroshot · 22,816 tokens