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 doc-draftergit 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/doc-drafter)<a href="https://agentmods.dev/skills/charlie947/life-automation-skills/doc-drafter"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/doc-drafter/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/doc-drafter"><img src="https://agentmods.dev/badge/skills/charlie947/life-automation-skills/doc-drafter.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 | $0.00124 | $0.01885 |
| Opus 5.5 | $0.00050 | $0.00754 |
| Sonnet 5.5 | $0.00025 | $0.00377 |
| Haiku 4.5 | $0.00012 | $0.00188 |
Grade A, and why
doc-drafter 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 — 104 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 the user wants a clean first draft of a business or legal document, built from a short brief:
- "Draft a contract" / "draft an SOW" / "draft an NDA / proposal / MSA"
- "Give me a first draft of this doc" / "write me a first draft"
- "Turn these notes into a statement of work"
- Any request to go from a brief to a structured document, ready for the user (and, for anything legal, a qualified professional) to review and finish.
Do not use it to give legal advice, to present anything as final or ready to sign, or to send a document to a counterparty. The output is always a draft.
What it needs (setup)
The core deliverable is a Markdown draft, which needs no connector at all. It is produced in the conversation and can be read, copied, and refined on the spot. Two optional native connectors let you file or formalise it:
- Google Drive connector (optional, write). Saves the finished draft as a file in the user's Drive, and reads a reference document the user points you at (an old contract, a house template).
- PandaDoc connector (optional). Lists the user's existing templates and creates a PandaDoc document from one of them, so the draft can move into a real signing workflow.
Be honest about the limits:
- The PandaDoc connector builds a document from an existing template. It does not turn free prose into a formatted, branded PandaDoc document on its own. If the user has no suitable template, the deliverable stays the Markdown draft (which they can paste into their own template).
- A document created in PandaDoc is a live object in the user's account. Only create one on explicit confirmation, and never send it for signature from here.
- Neither connector is required. If neither is connected, deliver the Markdown draft in the conversation and say what filing options would need which connector.
Safety rules (HARD)
This skill touches legal and financial content, so the bar is higher than usual. These are not optional.
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 · 104 lines · 124 tokens per session scan A 5863435393ec
doc-drafter is a skill published in the GitHub repository charlie947/life-automation-skills (34 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 1,885 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.
doc-drafter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doc-draftercharlie947/life-automation-skills | Skill | 34 | 2mo ago | MIT | A | 124 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |