bf-clarify

bf-clarify is a skill for Claude Code from chan4lk/specclaw. It costs 445 tokens per session (6,083 once invoked), scanned A, original, MIT.

A clarification-question generator for Specclaw analysis notes. It turns uncertainties, conflicting documents, missing decisions, and unused code paths into a numbered question file grouped by types such as decision, data, scope, and defect.

In plain words
What is it for?
Use it after analysis to create or update `.specclaw/analysis/clarifications.md`, including extracted questions and standard project questions.
Why use it?
It makes assumptions and unresolved choices explicit instead of leaving them buried in analysis notes. The resulting questions can be answered through a shared resolution process.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the specclaw plugin — 32 skills, 21 agents shipped together

Good fit Use it after analysis to create or update .specclaw/analysis/clarifications.md, including extracted questions and standard project questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chan4lk/specclaw/bf-clarify
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.

Any agent
npx skills add chan4lk/specclaw --skill bf-clarify
Clone the repo
git clone --depth 1 https://github.com/chan4lk/specclaw

Made for: Claude Code.

Or install specclaw, the plugin that ships this one along with the rest of its 32 skills, 21 agents.

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 bf-clarify

README.md
[![agentmods](https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-clarify.svg)](https://agentmods.dev/skills/chan4lk/specclaw/bf-clarify)
Your own site
<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-clarify"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-clarify.svg" alt="Measured on agentmods" height="20"></a>
Per session 445 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,083 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00445 $0.06083
Opus 5 $0.00222 $0.03041
Sonnet 5 $0.00089 $0.01217
Haiku 4.5 $0.00044 $0.00608

Measured 3d ago against content hash 7e7c31c353d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bf-clarify 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 3d 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.

plugins/specclaw/skills/bf-clarify/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specclaw bf-clarify

First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).

Turn the implicit uncertainty in .specclaw/analysis/*.md, plus the shaping questions no amount of code extraction can surface, into one explicit, numbered decision record. Read-only side-command — no specclaw-validate-change call, no <change> involved, matching the analyze/architecture/domain/rebuild-plan pattern.

Three question families share one clarifications.md and one --resolve pipeline — see templates/clarifications.md's HTML comment for the authoritative field-by-field breakdown:

  • CQ-NNN — extracted from .specclaw/analysis/*.md by the extraction agent (unchanged from before this upgrade). Allocated per-repo, in extraction order.
  • SQ-NNN — the standard bank (references/clarify-standard-questions.md, shipped with the plugin). IDs are fixed by the bank file itself, not allocated per-repo — SQ-001 means "target platform" in every project. Type/Blocking/Options/Proposed default are spliced in verbatim from the bank file by render, identical everywhere; only Finding/Why it matters/Source/Answer are project-specific.
  • UQ-NNN — per-repo custom questions from .specclaw/analysis/custom-questions.md, ingested by render directly (no agent involved). Allocated per-repo, in file order. render scaffolds this file itself: the first time a Mode A run (default or --bank-only) finds nothing at .specclaw/analysis/custom-questions.md, it copies templates/custom-questions.md there verbatim, and the run summary reports the scaffold. Edit the scaffolded file and re-run to turn its questions into real UQ-NNNs. The invariant that matters most: once anything exists at that path — even an empty file, even a malformed one — it is never overwritten, re-rendered, or otherwise touched again, by any later run, no matter how it got there or what it contains. It becomes user-authored the moment it exists. De-duplicated by each question's original heading text, recorded in its Source field — editing an already-ingested heading's wording later does not retroactively rewrite the rendered UQ-NNN; it reads as a brand-new question with a new ID. Edit the rendered question in clarifications.md instead if you want to change it.

Three modes, chosen by which flag the user's invocation carries: --resolve selects Mode B, --options-pack selects Mode C, neither selects Mode A. Mode A additionally accepts --bank-only. The three flags are mutually exclusive — if an invocation carries more than one, say so and ask which was meant rather than picking one. Mode C runs no extraction, spawns no bank agent, and writes neither clarifications.md nor decisions.md: it is a read-and-package pass over what Modes A and B already wrote.

Read the full file on GitHub · 130 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. 3d ago First seen · 130 lines · 0 tokens per session scan A 7e7c31c353d2

Subscribe to this mod's changes

bf-clarify is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 4d ago), licensed MIT. It adds 445 tokens to every session and 6,083 once invoked, about $0.0022 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 2026-09-05.

Related

Other skills, from other repositories

upload-assets

An asset-upload workflow that sends files to a console’s content-delivery network and prepares a review-request payload for a person to submit.

TOKTOKHAN-DEV/agent-company · 2 tokens

review-spec

A workflow for comparing an existing feature specification with the project's review checklist and implementation. It looks for missing requirements, differences between documented screens and actual screens, and lessons from rejected submissions.

TOKTOKHAN-DEV/agent-company · 2 tokens

wire-sdk

An SDK integration guide for 앱인토스, a platform for building apps inside Toss. It covers permissions, persistent storage, sharing links, screen controls, safe-area spacing, and secure WebSocket connections.

TOKTOKHAN-DEV/agent-company · 2 tokens

optimize-seo-geo

A workflow for filling only the SEO and GEO sections of a post's front matter. SEO helps a page appear in search results, while GEO prepares information for answer systems that may quote or cite it.

TOKTOKHAN-DEV/agent-company · 6 tokens

write-spec

A feature-specification workflow that turns a feature request into a Markdown file describing screens, acceptance checks, boundaries, and unanswered questions.

TOKTOKHAN-DEV/agent-company · 2 tokens

delegating-work

Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…

rundesk-ai/rundesk-cli · 76 tokens