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/rsdouglas/janee/agents-mdgit clone --depth 1 https://github.com/rsdouglas/janeeWhat 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 | $0.00482 | $0.00482 |
| Opus 5 | $0.00241 | $0.00241 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
janee 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 2d 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.
What it actually says
AGENTS.md
Guide for AI agents working on Janee.
What Must Never Be Forgotten
Security Guardrails
This is a security product. Non-negotiable rules:
- Never log credentials, tokens, or private keys
- Secrets must be encrypted at rest
- Validate all inputs (especially file paths and service names)
- Document security implications in PRs
See docs/POLICIES.md for full security policies.
Documentation Requirements
Always update:
docs/CHANGELOG.md— Add entry under[Unreleased]- Tests for new features or bug fixes
Update only if behavior changes:
README.md— New CLI commands, features, config optionsSKILL.md— Agent-facing changes (new tools, auth types)docs/— Significant features or architecture changes- RFC status — Update from Draft → Implemented
See docs/CONTRIBUTING.md for full PR checklist.
Release Process
1. Bump Version
npm version patch # X.Y.Z → X.Y.(Z+1) — bug fixes
npm version minor # X.Y.Z → X.(Y+1).0 — new features
npm version major # X.Y.Z → (X+1).0.0 — breaking changes
2. Update Changelog
Move [Unreleased] entries to new version section:
## [Unreleased]
_(empty)_
## [X.Y.Z] - YYYY-MM-DD
### Fixed
- Bug fix description (#issue)
Commit separately:
git add docs/CHANGELOG.md
git commit -m "docs: Update changelog for vX.Y.Z"
3. Publish
git push && git push --tags
npm publish --access public
4. Verify
npm view @true-and-useful/janee version
Repo Invariants
- Tests: Colocated with source (
*.test.ts) - Agent docs:
SKILL.md(usage),AGENTS.md(this file, development) - Preferred commit prefixes:
feat:,fix:,docs:,test:
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.
- 2d ago First seen · 73 lines · 482 tokens per session scan A 0b25310b3bf2
janee AGENTS.md is an instructions file published in the GitHub repository rsdouglas/janee (30 stars, last pushed 5mo ago), licensed MIT. It adds 482 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端（src/）.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.