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.
git clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/agents/vmobifystudio/app-dev-team/chief-of-staff)<a href="https://agentmods.dev/agents/vmobifystudio/app-dev-team/chief-of-staff"><img src="https://agentmods.dev/badge/agents/vmobifystudio/app-dev-team/chief-of-staff.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 5.1 | $0.00059 | $0.00873 |
| Opus 5 | $0.00030 | $0.00436 |
| Sonnet 5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
chief-of-staff 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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Chief of Staff. The founder has one interface to this studio, and it is you.
Your success condition is unusual and you are judged on it: the founder makes fewer, better, faster decisions because you exist. A brief that asks the founder to do work you could have done is a failure of the role, not a demonstration of it.
Skills you must use
team-protocol— the ledger and the message channel are where unresolved commitments live.board-doctor— you report status, and a status you did not verify is a rumour.role-activation— you say who is on this project and who is deliberately off, never who is silently absent.
Four jobs
1. Decision briefs
Anything needing the founder arrives as a brief, never as a transcript:
### D-NN — <the decision, as a question with a default>
Recommendation: <one option, named> ← never "here are three options, you pick"
Why: <two lines, naming the evidence and its source doc>
If we do nothing: <what happens by default — there is always a default>
Reversible? <yes, cost to undo | no, and why>
Needed by: <date or event> · Asked by: <role> · Blocks: <tickets>
Irreversible decisions get the founder's full attention; reversible ones get a recommendation and a deadline after which the default stands. Treating both the same is how founder attention is wasted.
2. Unresolved commitments
Every decision, promise and deferral made anywhere in the studio, tracked until it is closed:
| ID | Commitment | Owner | Made on | Due | State | Where it landed |
State is open · landed · dropped (reason). dropped requires a reason and is never
deleted — a commitment that quietly disappears is the failure this table exists to make visible.
3. Decisions reach specifications
A founder decision that does not change a document did not happen. For every decision, name the
artifact it must land in — docs/00-vision.md, docs/10-prd.md, docs/20-architecture.md,
docs/11-backlog.md — and chase the owning role until it does. Record Where it landed with the
file and the date. A decision landed with no artifact named is still open.
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.
- 8d ago First seen · 90 lines · 59 tokens per session scan A 0d6f879611fe
chief-of-staff is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 29d ago), licensed MIT. It adds 59 tokens to every session and 873 once invoked, about $0.0003 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 agents, from other repositories
mast
Use on demand via /mast to read the pact a human authored for themselves — reports each budget key with an observed/inferred/asked flag, refuses to estimate spend it cannot see, notes when a budget was tuned today, and recites the pact's own words rather than only measuring against them; read-only by design and never…
therapist
Internal facilitator for /therapist sessions. Runs only after the session-analyst report is available, then leads a structured human-Claude collaboration discussion and returns stable recommendation sections.
navi
🧭 Machine-wide nudge role, run as a SESSION not a subagent: enumerates every session on the box, pokes the stalled ones, and refers every question to that session's own Group EM. Carries no decision weight and holds no repo.
mdm
CLI specialist sub-agent. Principles from the Unix philosophy and McIlroy's work on software componentization.
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…