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 managing-personal-crmgit 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/managing-personal-crm)<a href="https://agentmods.dev/skills/jrgilbertson/the-rookery/managing-personal-crm"><img src="https://agentmods.dev/badge/skills/jrgilbertson/the-rookery/managing-personal-crm/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/managing-personal-crm"><img src="https://agentmods.dev/badge/skills/jrgilbertson/the-rookery/managing-personal-crm.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 | $0.00163 | $0.02675 |
| Opus 5.5 | $0.00065 | $0.01070 |
| Sonnet 5.5 | $0.00033 | $0.00535 |
| Haiku 4.5 | $0.00016 | $0.00267 |
Grade A, and why
managing-personal-crm 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 1mo 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Personal CRM
Maintain useful relationship meaning and connect current work to people without turning the CRM into an activity log, outreach quota, or second source of truth. Raw interactions stay in their sources, Person notes hold approved durable meaning, and dated relationship commitments stay in the canonical task system.
Resolve the mode
First, if the message asks to revisit or resume an action the user marked Deferred in a visible direct or catch-up CRM bundle, recover and present that exact visible proposal for a new decision. Revisit or resume is not approval: perform no write, source or destination recheck, or new discovery until the user makes a new exact decision about that proposal.
First determine whether the message continues a visible catch-up source
inventory, stage-one disposition bundle, or stage-two reconstruction. A
confirmation or revision of the required inventory, dispositions such as 1 active, 2 merge, a confirmation or correction of the visible interpretation
for the current person, an answer to its focused question, or a request to
resume its deferred reconstruction continues that exact catch-up stage. Read
references/catch-up.md before ordinary action handling
or mode selection. Preserve the visible recap and current person. A stage-two
reply does not start a new inventory or triage bundle and does not approve any
Person, Task, cleanup, or other destination effect; perform no write unless the
user later approves an exact separately proposed effect. If the required
preflight succeeds and that continuation will inspect any Person note for a
first or later stage-one triage bundle or inspect or reconstruct the current
person in stage two, read
references/relationship-contract.md
before the first such inspection or reconstruction. This applies immediately
after inventory confirmation, after recording dispositions from a prior
bundle, and before continuing a stage-two interpretation, focused answer, or
deferred reconstruction. An inventory-only turn that remains blocked need not
load the contract. Inventory decisions authorize only the confirmed preflight
scope. Stage-one dispositions are reviewed classifications, not approval to
change a Person note or perform cleanup; retain them in the visible recap and
perform no destructive action.
What ships with it
7 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.
- 1mo ago Changed 649c836f0abe
- 1mo ago First seen · 234 lines · 163 tokens per session scan A 3ebff411042d
managing-personal-crm is a skill published in the GitHub repository jrgilbertson/the-rookery (12 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 2,675 once invoked, about $0.0007 per session on Opus 5.5. 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
agentphone
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.
andreessen
Marc Andreessen-mode decision and productivity skill. A blunt, market-first operator that pressure-tests ideas, ventures, features, and career bets through Andreessen's actual frameworks — market dominates team and product; the only milestone that matters is product/market fit; bias to build over deliberate. Use when…
chief-customer-officer-advisor
Chief Customer Officer advisory for startups: retention decomposition (gross retention vs NRR honesty, churn root-cause taxonomy), customer segmentation strategy (differential investment across tiers + ICP fit scoring), CS team coverage model (pooled vs named CSM thresholds + ratio math), and CS team org evolution (CS…
diary
Unified Diary System: A context-preserving automated logger for multi-project development.
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.
chief-of-staff
C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically. Use when a founder question needs routing to the right…