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/mimurchison/claude-chief-of-staffWrote 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/commands/mimurchison/claude-chief-of-staff/enrich)<a href="https://agentmods.dev/commands/mimurchison/claude-chief-of-staff/enrich"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/enrich/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/commands/mimurchison/claude-chief-of-staff/enrich"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/enrich.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 | $0.00000 | $0.01215 |
| Opus 5 | $0.00000 | $0.00607 |
| Sonnet 5 | $0.00000 | $0.00243 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
enrich 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/enrich — Contact Enrichment
Description
Build and maintain your personal CRM. Scan communications for contact mentions, update interaction history, and surface relationships that need attention.
Arguments
all— Scan channels and update all contact files with new interactionsstale— Show contacts that haven't been engaged recently (based on tier cadence)<contact-name>— Enrich a specific contact's file with latest information
Contact Files
Location: ~/.claude/contacts/
Index: ~/.claude/contact-index.yaml (optional, for quick lookups)
Instructions
/enrich all
Scan connected channels for recent interactions and update contact files.
-
Scan channels for the last 24 hours (or since last enrichment):
- Email: Recent sent/received with known contacts
- Slack: DMs and mentions involving known contacts
- WhatsApp/iMessage: Recent messages with known contacts
- Calendar: Meetings that occurred with known contacts
-
For each interaction found:
- Look up the contact file in
~/.claude/contacts/ - If the file exists: Update "Last Interaction" and add to "Interaction History"
- If no file exists and the person seems important: Suggest creating one
- Add any new context learned (mentioned a project, changed roles, etc.)
- Look up the contact file in
-
Present a summary:
ENRICHMENT COMPLETE Updated: - Jane Smith — email exchange about platform migration (today) - Alex Chen — Slack DM re: hiring pipeline (today) New contacts detected (no file yet): - Pat Rivera ([email protected]) — 3 emails this week, discussed partnership → Want me to create a contact file? No updates needed: - [List of contacts with no new interactions]
/enrich stale
Check which contacts are overdue for engagement based on their tier.
- Read all contact files in
~/.claude/contacts/ - Compare last interaction date against tier cadence:
- Tier 1: Flag if no contact in 14+ days
- Tier 2: Flag if no contact in 30+ days
- Tier 3: Flag if no contact in 60+ days
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 · 166 lines · 0 tokens per session scan A ca8bf49cecf1
enrich is a command published in the GitHub repository mimurchison/claude-chief-of-staff (432 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,215 tokens. 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 commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.