butgo-specdrive-lab: Skill for Claude Code

.agents/skills/doc-work-ref/SKILL.md

doc-work-ref is a skill for Claude Code, Codex from butgo/butgo-specdrive-lab. It costs 37 tokens per session (2,441 once invoked), scanned A, original, MIT.

A workflow for checking or revising one specification document against only its configured reference documents. It uses project registries to identify the target and its allowed references.

In plain words
What is it for?
It is for running a reference check or revision on a configured target document and recording ref-prefixed history snapshots.
Why use it?
It limits the material considered during document work, reducing accidental use of unrelated documents or references.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex; $skill-name invocation.

This is butgo/butgo-specdrive-lab's own configuration. It tells Claude Code and Codex how to work on butgo-specdrive-lab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything butgo-specdrive-lab configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/butgo/butgo-specdrive-lab/main/.agents/skills/doc-work-ref/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/butgo/butgo-specdrive-lab

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for doc-work-ref

README.md
[![agentmods](https://agentmods.dev/badge/skills/butgo/butgo-specdrive-lab/doc-work-ref/github.svg)](https://agentmods.dev/skills/butgo/butgo-specdrive-lab/doc-work-ref)
Your own site
<a href="https://agentmods.dev/skills/butgo/butgo-specdrive-lab/doc-work-ref"><img src="https://agentmods.dev/badge/skills/butgo/butgo-specdrive-lab/doc-work-ref/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.

agentmods 80×15 button for doc-work-ref

Your own site · 80×15
<a href="https://agentmods.dev/skills/butgo/butgo-specdrive-lab/doc-work-ref"><img src="https://agentmods.dev/badge/skills/butgo/butgo-specdrive-lab/doc-work-ref.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.02441
Opus 5 $0.00018 $0.01221
Sonnet 5 $0.00007 $0.00488
Haiku 4.5 $0.00004 $0.00244

Measured 8d ago against content hash 0390963ef21a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

doc-work-ref 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.

.agents/skills/doc-work-ref/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Work Ref

Use this skill when a target document should be checked or revised against only its configured upper/reference documents.

This skill sits between $doc-work and $doc-work-bundle:

  • $doc-work reads one target document only.
  • $doc-work-ref reads the target document plus reference_docs only.
  • $doc-work-bundle reads the target document plus bundle_refs from doc-work-bundle-map.json.

Read First

Read these registries first:

specdrive/config/target-registry.json
specdrive/config/affected-docs-map.json

If the user did not provide a target key or document path, list target keys that have entries in affected-docs-map.json and stop.

Resolve the target key or path from target-registry.json, then find the matching entry in affected-docs-map.json by key or path.

If the user provided only a target and no action, read only the target metadata and affected-docs entry metadata. Show the action choices.

Supported actions for now:

  • reference
  • revise

For reference or revise, read:

  1. the resolved target document
  2. only documents listed in that entry's reference_docs

Do not read include_for_bundle or check_targets unless the user explicitly asks to do bundle or impact validation.

Do not inspect docs/history/** file contents unless the user explicitly asks for history lookup.

History Rules

If a ref action updates one document, save one history snapshot and one note for that document.

If a ref action updates multiple documents, save separate history snapshots and separate notes for each changed document.

Use the same timestamp for all history files created by one approved ref operation.

Ref history filenames must add ref after the timestamp:

yyyy-MM-dd_HHmmss_ref_<document-base>_codex-reinforced.md
yyyy-MM-dd_HHmmss_ref_<document-base>_codex-reinforced.note.md
yyyy-MM-dd_HHmmss_ref_<document-base>_dev-revised.md
yyyy-MM-dd_HHmmss_ref_<document-base>_dev-revised.note.md

For project documents, use:

Read the full file on GitHub · 303 lines

Changes

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.

  1. 8d ago First seen · 303 lines · 37 tokens per session scan A 0390963ef21a

Subscribe to this mod's changes

doc-work-ref is a skill published in the GitHub repository butgo/butgo-specdrive-lab (1 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,441 once invoked, about $0.0002 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.