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/yoanwai/agent-manager/agents-mdgit clone --depth 1 https://github.com/YoanWai/agent-managerWrote 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/yoanwai/agent-manager/agents-md)<a href="https://agentmods.dev/instructions/yoanwai/agent-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/yoanwai/agent-manager/agents-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 | $0.01092 | $0.01092 |
| Opus 5 | $0.00546 | $0.00546 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
agent-manager 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent notes
Project context for coding agents. Human setup and PR conventions live in .github/CONTRIBUTING.md.
Build and test
go run . # run the TUI
go build ./...
env -u TMUX TMUX_TMPDIR=/tmp/amtest go test ./...
The suite drives a real tmux server. When your own shell already runs inside
tmux, $TMUX overrides TMUX_TMPDIR and the tests land on the live socket,
so env -u TMUX is mandatory, never a bare go test. Keep the socket dir
short: TMUX_TMPDIR/tmux-<uid>/default must stay under 104 characters or
tmux silently falls back to the default socket. Never run tmux kill-server
or kill-session against the default socket; kill stray processes by PID.
Before finishing: gofmt -l . prints nothing, go vet ./... is clean.
Concurrent sessions
Multiple agent sessions share this checkout. Do feature work in an isolated
git worktree (git worktree add), or your edits get swept into someone
else's commit. Branch from origin/main after a fetch, not from the local
main ref.
Releases
Cut from a clean worktree at the tag, with goreleaser run locally; there is no release workflow in CI.
tag=v0.30.0 # the release being cut
git tag "$tag" && git push origin "$tag"
git worktree add /tmp/amrel "$tag"
cd /tmp/amrel && GITHUB_TOKEN="$(gh auth token)" AUR_KEY="$HOME/.ssh/aur_agent_manager" \
goreleaser release --clean
AUR_KEY is what publishes the Arch package: without it git_url templates
to empty, goreleaser skips that step, and the release still reports success
while the AUR package goes stale.
The notes carry more than the generated list of pull requests:
- A summary in your own words, at the top, saying what the release gives someone who installs it. Two or three sentences, the change first and the mechanism second. The generated list says which pull requests landed; it does not say what is different now.
- A
## Highlightssection above## What's Changed, holding short bullets, one per thing the release gives someone. The manager reads exactly those bullets into its messages panel, so write them for a modal: a sentence each, feature and fix language, no pull request numbers. Prose in that section stays on the web page; only bullets travel. A release without the section falls back to the generated list, filtered tofeat,fixandperf. - Thanks to every contributor in the range, by handle. Read the merged pull requests, not only the generated list, and name what each one did.
- Thanks to whoever reported what got fixed, by handle. A bug someone took the time to write up is why the fix exists, and the reporter is usually not the author. Credit the release a feature builds on, too, when it extends someone else's work.
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.
- 3d ago First seen · 98 lines · 1,092 tokens per session scan A d8b90c350c59
agent-manager AGENTS.md is an instructions file published in the GitHub repository YoanWai/agent-manager (374 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,092 tokens to every session, about $0.0055 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
qwen-code AGENTS.md
AGENTS.md instructions for QwenLM/qwen-code, covering agents.md, working principles, simplicity first, common commands and building.
qwen-code CLAUDE.md
Claude Code instructions for QwenLM/qwen-code: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
awesome-gemini-cli-subagents GEMINI.md
Instructions for ankitmundada/awesome-gemini-cli-subagents, covering gemini.md, project overview, repository structure, subagent file format and communication protocol.
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.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
pi-ask AGENTS.md
Instructions for eko24ive/pi-ask, covering agents.md, project scope, project goals, tech stack and commands.