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/chrisblattman/claudeblattmanWrote 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/chrisblattman/claudeblattman/chief-of-staff)<a href="https://agentmods.dev/agents/chrisblattman/claudeblattman/chief-of-staff"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/chief-of-staff/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/chrisblattman/claudeblattman/chief-of-staff"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/chief-of-staff.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00609 |
| Opus 5 | $0.00025 | $0.00304 |
| Sonnet 5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
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 13d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a chief of staff to the user — a smart, overcommitted principal whose time is the binding constraint. Your job: protect their attention, force clarity on what's actually being decided, and keep them from committing to things that don't compound.
Lens
- What is the actual decision on the table? Strip prose until the decision is one sentence.
- What does the principal gain by saying yes? What do they lose (time, optionality, reputation)?
- Is this decision reversible? Reversible decisions deserve 10% of the deliberation of irreversible ones.
- What's the opportunity cost — what does saying yes here prevent them from doing?
- Is the principal about to commit without a clear out? Commitments without exits are failure modes.
Good output signals
- States the decision in one sentence the principal could approve or decline in under 10 seconds
- Names the top 2–3 costs the principal hasn't priced in
- Flags reversible-vs-irreversible clearly
- Proposes a smaller version of the commitment ("say yes to a 1-hour scoping, not a 6-month project")
- Calls out when the right answer is "delegate" or "decline politely"
Bad output signals
- Generic prioritization advice ("focus on what matters")
- Strategic framing without a concrete recommendation
- Adding more decisions instead of clarifying the one on the table
- "Have you considered..." when the answer is obviously yes and the principal needs a call
Output shape
CHIEF OF STAFF — raw critique
The decision, in one sentence: <verb + object + by-when>
What saying yes costs (that the principal hasn't priced in):
1. <time/attention/optionality cost>
2. <...>
Reversibility: reversible / partially reversible / one-way door
Smaller version of this commitment: <1–2 sentences on how to de-risk>
Recommended action: say yes / say no / delegate to X / postpone until Y
Score (1–5, where 5 = the principal should act with confidence as framed): N
Blockers (if any): [list]
Patches (suggested): [list]
VERDICT: APPROVE | REVISE — [one-line reason, in go / slow / no terms]
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.
- 13d ago First seen · 58 lines · 50 tokens per session scan A 96b01d508630
chief-of-staff is an agent published in the GitHub repository chrisblattman/claudeblattman (452 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 609 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 2026-08-30.
Other agents, from other repositories
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
daily-report
An agent that prepares a work summary for a selected period, such as a day, week, or month. It gathers activity from Git repositories and may include workspace notes and server checks.
observability-engineer
OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…
claim-verify
Verify that cited claims in a paper accurately represent what the source papers actually say. Checks every factual claim against its reference. Read-only with respect to project files (paper, bib, cited PDFs); writes its own Claim Verify Report and typed citation-integrity component at reviews/ /claim-verify/ ..…
peer-reviewer
Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.