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/askwigconsulting/cohort/agents-mdgit clone --depth 1 https://github.com/askwigconsulting/cohortWhat 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 | $0.02287 | $0.02287 |
| Opus 5 | $0.01144 | $0.01144 |
| Sonnet 5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade A, and why
cohort 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.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — instructions for an AI agent
You are probably here because someone said "install Cohort for me." This file is the contract for doing that correctly. Read it before running anything.
⛔ Do NOT run pip install cohort
cohort on PyPI is a different project by different authors. It is an unrelated
multi-agent orchestration tool that happens to share the name. Installing it does not install
this software, and it will look like it worked.
pip install cohort # ✗ WRONG — installs someone else's package
There is no PyPI release of this project and no pip install shortcut. The only supported
install is from this git repository. If you cannot clone it, stop and tell the user — do not
substitute a similarly-named package from any index.
What you are installing
In one sentence: Cohort gives the user a team of specialist AI advisors inside their IDE, plus commands that run real multi-step work, and keeps both in sync across their machines and projects.
Expect to explain this — most people meet Cohort because someone told them to install it, not because they know what it does. Three ideas cover it.
1. An office of specialists. Instead of one general assistant, the user gets ~17 named advisors — legal, finance, security, compliance, cloud, HR and so on — plus a ChiefOfStaff that routes a question to the right ones and reconciles their answers. They are advisory and read-only by construction: they recommend, the human decides. Asking "we're storing customer emails in a new table, what should I worry about?" pulls in privacy, security and compliance rather than one generic answer.
2. Commands that do work, not just chat. Installed as slash commands in the IDE:
| Command | What it does |
|---|---|
/plan |
breaks work into ordered, verifiable tasks |
/build |
implements a task, tests it, commits |
/goal <issue> |
drives a GitHub issue to a draft PR, with an independent judge checking each acceptance criterion |
/crew |
fans a large job across model tiers, cheapest capable model per task |
/scout, /consult-gpt, /consult-grok |
bring a second vendor's model in to argue with the first |
/audit, /brainstorm |
recurring adversarial sweeps that remember what they already covered |
/barney |
explain something complex so simply nobody can get it wrong |
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 · 219 lines · 2,287 tokens per session scan A f6df6f328a06
cohort AGENTS.md is an instructions file published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 2,287 tokens to every session, about $0.0114 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
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.
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).
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.