Borrowing it
Nothing to install: this file belongs to butgo/butgo-specdrive-lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/butgo/butgo-specdrive-lab/main/.agents/skills/doc-work/SKILL.mdgit clone --depth 1 https://github.com/butgo/butgo-specdrive-labWrote 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/butgo/butgo-specdrive-lab/doc-work)<a href="https://agentmods.dev/skills/butgo/butgo-specdrive-lab/doc-work"><img src="https://agentmods.dev/badge/skills/butgo/butgo-specdrive-lab/doc-work/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/butgo/butgo-specdrive-lab/doc-work"><img src="https://agentmods.dev/badge/skills/butgo/butgo-specdrive-lab/doc-work.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 | $0.00059 | $0.03552 |
| Opus 5 | $0.00030 | $0.01776 |
| Sonnet 5 | $0.00012 | $0.00710 |
| Haiku 4.5 | $0.00006 | $0.00355 |
Grade A, and why
doc-work 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 8d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Work
Use this skill as the basic single-document entry point for specdrive doc-stage work.
Read First
Read this registry first:
specdrive/config/target-registry.json
If the user did not provide a target key or document path, list the available target keys and stop.
If the user provided a target key, resolve it from targets.
If the user provided a document path, match it to a target by document_path when possible.
If the user provided only a target and no action, read only the target metadata and show the action choices.
Supported actions for now:
draftreinforcerevise
If the user provided a target and action, read only the resolved target document.
Do not read specdrive/config/affected-docs-map.json for this skill unless the user explicitly asks for reference or bundle checking.
Before generating an action prompt, check existing history filenames for the target under its doc-work history directory.
For project documents, use docs/history/projects/<project>/<document-base>/work/ where <document-base> is the target document filename without .md.
- For
draft, if any file matching*_dev-draft.mdexists for the target document base, report that a developer draft history already exists and stop. - For
reinforce, if any file matching*_codex-reinforced.mdexists for the target document base, report that a Codex reinforced history already exists and stop. - For
revise, allow multiple runs. Do not stop when*_dev-revised.mdalready exists. - Do not inspect the contents of existing
docs/history/**files unless the user explicitly asks for history lookup.
Output
Output Fencing Rules
When showing a document preview, wrap the whole preview with ~~~markdown, not triple backticks.
This prevents inner Markdown examples such as code blocks, JSON examples, or text snippets from closing the outer preview block.
Inside a document preview, prefer indented examples or inline code for short snippets.
If fenced examples are needed inside the preview, use triple backticks only because the outer preview uses tildes.
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.
- 8d ago First seen · 343 lines · 59 tokens per session scan A fc85ef26e4e4
doc-work is a skill published in the GitHub repository butgo/butgo-specdrive-lab (1 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 3,552 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
PDF files: create, read, merge, fill, OCR, edit text.
excel-author
Build auditable financial workbooks headless via openpyxl.
siyuan
Query and edit a SiYuan knowledge base via its API.