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 charlie947/life-automation-skills --skill crm-hygienegit clone --depth 1 https://github.com/charlie947/life-automation-skillsWrote 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/charlie947/life-automation-skills/crm-hygiene)<a href="https://agentmods.dev/skills/charlie947/life-automation-skills/crm-hygiene"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/crm-hygiene/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/charlie947/life-automation-skills/crm-hygiene"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/crm-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.01940 |
| Opus 5.5 | $0.00049 | $0.00776 |
| Sonnet 5.5 | $0.00025 | $0.00388 |
| Haiku 4.5 | $0.00012 | $0.00194 |
Grade A, and why
crm-hygiene 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 2mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Use it when a contact table has gone messy and needs a careful tidy:
- "Clean my CRM" / "tidy my contacts" / "fix my contact list"
- "Dedupe my contacts" / "merge duplicate contacts" / "find the duplicates"
- "Fill in the blanks on my contacts" / "enrich my records"
- "Normalise the formatting" (names, emails, phone numbers, company names)
- Any request to find, review, or resolve duplicate or half-filled records in Airtable, Notion, or HubSpot.
Do not use it to merge or delete records without a confirmed change list, and do not use it to invent contact details that are not in a real source.
What it needs (setup)
One native Claude connector, read and write, login-only OAuth, no build:
- Airtable connector: list, search, read, create, update, and delete records in a base. Reverting an action undoes only the most recent write.
- or the Notion connector: query a data source, read, create, and update pages (records). Notion has no hard-delete. A duplicate is retired by flagging it and archiving to Trash, which the user does in the Notion UI. Nothing is erased.
- or the HubSpot connector: read, create, and update contact, company, and deal records in the CRM. HubSpot archives rather than hard-deletes, and an archived record is recoverable for a limited window. Treat every merge or archive here the same way, propose it and act only on the user's yes.
Honest limits, say them plainly if they matter:
- No safe one-click merge to rely on. The skill never trusts an automatic merge across records. A merge is: read both, compose the merged record, write the survivor first, then retire the loser second. The skill always does it in that order so nothing is lost if it stops midway.
- Deletes barely undo. Airtable can revert only its most recent action. Notion cannot delete at all through the connector. HubSpot archives rather than hard-deletes, recoverable only for a limited window. So the skill proposes, confirms, then writes.
- No built-in enrichment. These connectors do not look anyone up. Blanks are filled only from a real source (see the safety rules), never guessed.
- Interface-only Airtable bases cannot be edited through the table tools. If access is interface-only, say so and stop.
What ships with it
1 file 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.
- 2mo ago First seen · 92 lines · 123 tokens per session scan A 1da562685354
crm-hygiene is a skill published in the GitHub repository charlie947/life-automation-skills (34 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,940 once invoked, about $0.0005 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 2026-08-30.
crm-hygiene compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crm-hygienecharlie947/life-automation-skills | Skill | 34 | 2mo ago | MIT | A | 123 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |