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 commands/askwigconsulting/cohort/office-setupgit 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 | $0.00021 | $0.00858 |
| Opus 5 | $0.00010 | $0.00429 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
office-setup 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailor this machine's Cohort office to its owner. You are conducting a short
interview, then driving the cohort CLI with the answers. Every change is
shown to the user and approved before it lands; you never write silently.
1 — Wiring (skip what cohort status --json shows is already done)
Ask, one question at a time:
- Company office? "Does your organization maintain a shared Cohort repo (a fork with your company's roster)?" If yes, collect its URL and default branch — updates and improvement proposals will flow to it.
- IDEs. Which of claude / codex / cursor they use.
- Roster. Show the roster (
ls <source>/canonical/agents/) with one-line descriptions and ask which agents match their work. A solo developer rarely needs the full office;chief-of-staffshould stay unless they insist.cloud-architectcovers AWS, Azure, and GCP in one advisor — include it only if the user runs on a cloud at all (a user on none needs it not); it asks which vendor when consulted.
Then run the flags form (never the bare interactive form — you are the interview):
cohort setup --ide <ides> --agents <subset|all> [--company-url <url> --company-branch <branch>]
After it lands, run cohort status and look for ! unmanaged: lines — pre-existing
agents/commands sitting loose in ~/.claude/. For each, ask whether to adopt it into
the office (cohort adopt <path> — the original is backed up, and adopted agents
become advisory read-only) or leave it unmanaged and invisible to ChiefOfStaff's
directory. Never adopt without asking.
2 — Office context (who the advice is for)
Interview briefly: role, domain/industry, primary stack, team size, and any
constraints that should color every agent's advice (regulated industry,
open-source, solo founder, …). Then draft the personal context memory — it
belongs to my office (~/.cohort/my/), never the shared clone, and its name
is reserved so it can never mask a company-shipped office-context:
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 · 72 lines · 21 tokens per session scan A fa138bee862d
office-setup is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 21 tokens to every session and 858 once invoked, about $0.0001 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 commands, from other repositories
claude-flow-swarm
Coordinate multi-agent swarms for complex tasks.
bootstrap
PACT session-start ritual — identify the session team (platform-provisioned), secretary spawn, paused-state surface, bootstrap marker.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff
Package current state for the next agent.
xdo
Direct development by the Main Agent.