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/brian-egan/jazz_agent/agents-mdgit clone --depth 1 https://github.com/Brian-Egan/jazz_agentWhat 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 | $0.01979 | $0.01979 |
| Opus 5 | $0.00989 | $0.00989 |
| Sonnet 5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
jazz_agent 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 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for the coding agent implementing this repository.
This file is for the implementer. The runtime contract for the Claude Project that
queries the finished system is a different document:
docs/claude-project-instructions.md. Do not
conflate them.
Read first
docs/ARCHITECTURE.md— the specification. Issues reference it by section.docs/DECISIONS.md— why things are the way they are.docs/DATA_MODEL.md— schema and the queries it exists to serve.
docs/original-prd.md is the original PRD, kept
verbatim. It is superseded in several places. Where the PRD and ARCHITECTURE.md disagree,
ARCHITECTURE.md wins and the relevant ADR names the superseded section. Do not implement
from the PRD directly.
How to pick up work
gh issue list --state open --milestone v1
Take the lowest-numbered issue whose Blocked by dependencies are all closed. Do not
start a blocked issue. If everything open is blocked, say so rather than guessing at
scaffolding.
One issue per branch, one commit series per issue, reference the issue in the commit message so it closes on merge. Do not batch multiple issues into one change.
If an issue's acceptance criteria turn out to be wrong or impossible, say so on the issue and stop. Do not silently redefine the work.
Invariants
These are not style preferences. Breaking any of them breaks a decision recorded in an ADR.
1. core/ and ports/ must never import adapters/
core/ is pure domain logic and performs no I/O. ports/ holds Protocols only. This is
what makes the system portable per PRD 8.6, and it is enforced by an import-linter
contract in CI. If you find yourself wanting an HTTP call inside core/, the logic belongs
in pipeline/ and the data should be passed in.
2. Only config.py reads the environment
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 First seen · 189 lines · 1,979 tokens per session scan A 5b645c30b18e
jazz_agent AGENTS.md is an instructions file published in the GitHub repository Brian-Egan/jazz_agent (0 stars, last pushed 7d ago), licensed MIT. It adds 1,979 tokens to every session, about $0.0099 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.