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 skills add jrgilbertson/the-rookery --skill personal-chief-of-staffgit clone --depth 1 https://github.com/jrgilbertson/the-rookeryWrote 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/skills/jrgilbertson/the-rookery/personal-chief-of-staff)<a href="https://agentmods.dev/skills/jrgilbertson/the-rookery/personal-chief-of-staff"><img src="https://agentmods.dev/badge/skills/jrgilbertson/the-rookery/personal-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/skills/jrgilbertson/the-rookery/personal-chief-of-staff"><img src="https://agentmods.dev/badge/skills/jrgilbertson/the-rookery/personal-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 | $0.00101 | $0.00908 |
| Opus 5 | $0.00051 | $0.00454 |
| Sonnet 5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
personal-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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Chief of Staff
Help the user review current evidence, correct their sources, and choose what comes next. Existing systems remain authoritative; keep the review in the conversation until the user approves specific source changes.
Route the current message
Read source-behavior.md and review-bundle.md before source access on every path. Then resolve the message in this order:
- Visible action decisions: bind approvals, edits, deferrals, and skips to the exact displayed bundle and its originating mode. Load that mode's reference and follow the shared application rules, including the CRM companion rules for relationship-derived effects. A bare number is usable only when the visible context identifies its action.
- Answers to a Frontier Round: interpret numbers against the most recent question round and continue the mode and phase that asked it.
- A new review: select one mode below. An explicit mode wins.
- Cross-source context for another workflow: retrieve only what the caller's decision needs, return the context with its Source Access Audit, and leave the narrower operation with the caller. This path opens no mode.
An action-only reply performs the current pre-write checks and readback without new review discovery. A reply to an earlier bundle in an unfinished run continues that run: Wind-down Phase 1 decisions lead into Phase 2 without a new review request.
If a message decides actions and requests a new review or cross-source context, resolve the old decisions first. Finish Phase 2 when the decisions belong to a Wind-down Phase 1 bundle. Then begin the newly requested read-only discovery; its evidence cannot reinterpret the earlier approval. Use one audit, separating Action access from Review discovery or Context discovery.
| Mode | Request | Read before retrieval |
|---|---|---|
| Wind-down | Close the day, complete the daily journal, reflect, prepare tomorrow, or run a daily review, including a scheduled wind-down | wind-down.md |
| Weekly | Complete or discuss a weekly review | weekly.md |
| Quarterly | Complete or discuss a quarterly review | quarterly.md |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · -85 lines 44399c6c7ddf
- 12d ago First seen · 169 lines · 101 tokens per session scan A 75a7327e5235
personal-chief-of-staff is a skill published in the GitHub repository jrgilbertson/the-rookery (5 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 908 once invoked, about $0.0005 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 skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
slack-messaging
Use when writing, drafting, scheduling, or improving a Slack message, announcement, or reply sent via the Slack MCP tools (slacksendmessage, slacksendmessagedraft, slackschedulemessage). Covers Slack markdown formatting, message structure, thread etiquette, reactions, and scheduling, and points to the right dialect…