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 mishahanin/heading-os --skill crmgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/crm)<a href="https://agentmods.dev/skills/mishahanin/heading-os/crm"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/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/mishahanin/heading-os/crm"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/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 | $0.00015 | $0.01564 |
| Opus 5 | $0.00008 | $0.00782 |
| Sonnet 5 | $0.00003 | $0.00313 |
| Haiku 4.5 | $0.00002 | $0.00156 |
Grade A, and why
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 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal CRM
Manage contacts, log interactions, track relationship health, and surface follow-up priorities.
Workspace-Aware Paths
This skill works across both CEO and exec workspaces. On startup, read .workspace-identity.json from the workspace root to determine workspace type.
| Resource | CEO Workspace | Exec Workspace |
|---|---|---|
| Personal contacts | crm/contacts/ |
personal/crm/contacts/ |
| Tribe contacts (shared) | crm/contacts/ (type: tribe*) |
corporate/crm/contacts/ (read-only) |
| CRM config | crm/config.md |
corporate/crm/config.md |
| People index | context/people.md |
context/people.md (personal root) |
All path references below (e.g., crm/contacts/) should be resolved using this mapping based on the detected workspace type.
Tribe contacts are corporate-wide. In exec workspaces, Tribe member contacts live in corporate/crm/contacts/ (read-only, synced from CEO workspace). When searching or displaying contacts, always check BOTH personal and corporate CRM directories. When logging interactions for Tribe members in exec workspaces, log to the personal copy if it exists, otherwise note that the contact is read-only corporate.
Variables
$ARGUMENTS— Subcommand and parameters. Format:[action] [details]
Actions
Parse the first word of $ARGUMENTS to determine the action:
Read references/actions.md before you run any action below. It holds the
full step sequence, the canonical-owner lookup, and the record templates. The
table names only the command lines and the guards.
| Action | Commands and guards | What it does |
|---|---|---|
radar (default, and the no-argument case) |
python scripts/crm-health.py. Admin role only, from .workspace-identity.json: python scripts/aggregate-crm.py for the company-wide view, and python scripts/generate-crm-dashboard.py for the full HTML dashboard. Execs never get the company-wide view. |
Relationship health dashboard, ordered RED, then YELLOW, then commitments due within 7 days, then GREEN. |
next |
python3 scripts/crm_next.py to build today's queue. Present all 3 drafts and WAIT. Send only what the CEO names, one at a time, with python3 scripts/send-email.py --to <addr> --subject "<subject>" --body "<body>". |
Top-3 priority follow-ups with drafts ready for per-draft CEO review. |
add |
Warn when email sits on the configured corporate mail domain and the type is neither tribe nor tribe-leadership (resolution: references/actions.md). On the CEO workspace only, and only for a deal-bearing external type: python scripts/odin-principles.py --type {relationship_type} [--stage {stage}] --json. |
Create the address book entity plus the relationship record, then index the contact in context/people.md. |
log |
No script. Ask which contact when several match. Suggest /crm add when none match. |
Add a dated interaction entry at the TOP of the Interaction Log, then bump last_touch. |
find |
Grep over crm/contacts/. No writes. |
Search name, company, title, region, type, and interaction history. |
update |
On the CEO workspace only, and only for a deal-bearing external type: python scripts/odin-principles.py --type {relationship_type} [--stage {stage}] --json. |
Change one profile field, then recalculate cadence when type changed. |
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.
- 5d ago Changed eb791d01f711
- 9d ago First seen · 116 lines · 15 tokens per session scan A da57b34df85b
crm is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 1,564 once invoked, about $0.0001 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 skills, from other repositories
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.