faq-capture

faq-capture is a skill for Claude Code, Codex from BreadchainCoop/labor.fun. It costs 46 tokens per session (1,237 once invoked), scanned A, original, MIT.

A skill for turning a reusable answer from a chat into a searchable FAQ card in a knowledge base. It uses an approval step and a stable identifier so repeating the same question updates one card instead of creating duplicates.

In plain words
What is it for?
Use it after answering recurring how-to, process, location, or explanation questions, provided the organisation has enabled the skill and the information is suitable for broad access.
Why use it?
It keeps useful answers from being lost in old conversations while avoiding duplicate entries.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/breadchaincoop/labor.fun/faq-capture
Any agent
npx skills add BreadchainCoop/labor.fun --skill faq-capture
Clone the repo
git clone --depth 1 https://github.com/BreadchainCoop/labor.fun

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 faq-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/faq-capture.svg)](https://agentmods.dev/skills/breadchaincoop/labor.fun/faq-capture)
Your own site
<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/faq-capture"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/faq-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.01237
Opus 5 $0.00023 $0.00619
Sonnet 5 $0.00009 $0.00247
Haiku 4.5 $0.00005 $0.00124

Measured 4d ago against content hash 3467b4c2c4fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faq-capture 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 4d 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.

container/skills/faq-capture/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Living FAQ Capture

When a question in chat gets a clear, reusable answer — the kind of thing someone else will ask again in a month — capture it as an FAQ card under artifacts/faq/ instead of letting the answer evaporate into scrollback.

This is opt-in per org (ENABLED_SKILLS). If you don't see this skill listed, don't do any of the below.

When to capture (use judgment)

Capture when the exchange was a genuine question with a durable answer: "how do I...", "what's the process for...", "where do I find...", "why does...".

Do not capture:

  • One-off, person-specific requests ("can you send me the Q3 numbers")
  • Anything that touches private/restricted information (see rules/access-control/privacy-policy.md) — an FAQ card defaults to open visibility and is meant to be broadly readable
  • Small talk, status updates, or anything without a real question+answer shape
  • A question you couldn't actually answer — see "Knowledge gaps" below instead

Step 1 — compute the deterministic slug (idempotency key)

Two different phrasings of the same question must land on the same card so re-asking updates it instead of creating a duplicate. Derive the slug yourself, exactly like this (mirrors src/faq-capture.ts faqSlug, which is unit-tested — match it precisely):

  1. Unicode-normalize (NFKD) and strip diacritics.
  2. Lowercase.
  3. Drop apostrophes/quotes (', , ", `) — "don't" and "dont" must collide.
  4. Replace every remaining run of non [a-z0-9] characters with a single -.
  5. Trim leading/trailing -.
  6. Cap at 80 characters, re-trimming a trailing - if the cut landed on one.
  7. Empty result → faq.

The card path is always artifacts/faq/<slug>.md.

Step 2 — check for an existing card (idempotent update, not duplicate)

Read /workspace/shared-kb/artifacts/faq/<slug>.md (read-only mount). If it exists, compare its title + body against what you're about to write:

  • Same question title and the new answer/source text is already present in the existing body → no-op. Don't request approval, don't write anything. Tell the user (if relevant) that this is already documented.
  • Different or missing → proceed to Step 3 with an update, not a fresh card (same path, so it overwrites rather than duplicating).

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 46 tokens per session scan A 3467b4c2c4fb

Subscribe to this mod's changes

faq-capture is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,237 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens