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/memandip/agman/claude-mdgit clone --depth 1 https://github.com/memandip/agmanWrote 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/memandip/agman/claude-md)<a href="https://agentmods.dev/instructions/memandip/agman/claude-md"><img src="https://agentmods.dev/badge/instructions/memandip/agman/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 | $0.01490 | $0.01490 |
| Opus 5 | $0.00745 | $0.00745 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
agman CLAUDE.md scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`install.sh`** — curl-pipe installer. How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — agman
Project-local instructions for AI coding agents working in this repo. These OVERRIDE default behavior. Read before making changes.
What this project is
agman (agent manager) switches complete config profiles for AI coding agents —
Claude Code, Codex CLI, Gemini CLI — the way AWS_PROFILE switches AWS accounts. A profile
is one config tree per tool under ~/.agman/<name>; agman use <name> activates it by
symlinking each tool's real config path (~/.claude, ~/.claude.json, ~/.codex,
~/.gemini) at the profile.
The problem it solves: people keep separate work/personal/client setups (instructions,
settings, rules, skills, agents, MCP servers, accounts) but the agent CLIs offer no first-class
way to switch between them. Env-var overrides don't generalize — Gemini CLI has no config-dir
override at all — so agman switches by symlink, which needs no shell integration and applies to
every new session machine-wide, IDE extensions included. Sessions and prompt history are kept in
shared state (~/.agman/.state) so claude --resume keeps working across profile switches;
only the persona is per-profile.
Architecture — what you're editing
bin/agman— the entire program. One pure-bash script, no dependencies.install.sh— curl-pipe installer.tests/run.sh— the test suite.tests/docker-session-*.sh— containerized upgrade/resume tests.docs/—design.md,roadmap.md,index.html(landing page)..github/workflows/—ci.yml(tests + shellcheck),homebrew.yml(release → tap PR).
Hard constraints (do not break these)
- Bash 3.2 compatible. Stock macOS ships bash 3.2. No associative arrays, no
mapfile, no${var,,}. Parallel indexed arrays are used deliberately — keep that style. - No runtime dependencies. Pure bash + coreutils only. Don't add jq, python, node, etc.
- POSIX-portable. Must work on macOS, Linux, WSL, and Git Bash.
- Never touch symlinks agman didn't create. The safety model (refusing foreign symlinks,
refusing to remove the active profile, backing up originals to the
globalprofile) is load-bearing. Preserve it. - Two version counters, different jobs.
AGMAN_VERSIONis the release version (semver).LAYOUT_VERSIONis the on-disk profile layout — bump it only when the~/.agmanlayout changes in a way that needs migration, and add the migration path.
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.
- 4d ago First seen · 111 lines · 1,490 tokens per session scan A 92f78bbbaf4f
agman CLAUDE.md is an instructions file published in the GitHub repository memandip/agman (4 stars, last pushed 15d ago), licensed MIT. It adds 1,490 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
crewplane AGENTS.md
Instructions for crewplaneai/crewplane, covering agents.md, repo facts, read first, repo map and project heuristics.
AgentsMesh CLAUDE.md
Claude Code instructions for AgentsMesh/AgentsMesh, covering claude.md, project overview, components, development environment and quick start.
crewplane copilot-instructions.md
Instructions for crewplaneai/crewplane: Use AGENTS.md as the canonical repository instructions.
crewplane CLAUDE.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.
crewplane GEMINI.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.
co-evolution CLAUDE.md
Instructions for alanshurafa/co-evolution, covering co-evolution - cross-ai document refinement, default rule, components, co-evolution skill (skills/co-evolution/) and co-evolve bouncer (co-evolve-bouncer.sh).