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 chan4lk/specclaw --skill bf-clarifygit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/bf-clarify)<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>- 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 | $0.00445 | $0.06083 |
| Opus 5 | $0.00222 | $0.03041 |
| Sonnet 5 | $0.00089 | $0.01217 |
| Haiku 4.5 | $0.00044 | $0.00608 |
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.
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/*.mdby 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-001means "target platform" in every project.Type/Blocking/Options/Proposed defaultare spliced in verbatim from the bank file byrender, identical everywhere; onlyFinding/Why it matters/Source/Answerare project-specific.UQ-NNN— per-repo custom questions from.specclaw/analysis/custom-questions.md, ingested byrenderdirectly (no agent involved). Allocated per-repo, in file order.renderscaffolds this file itself: the first time a Mode A run (default or--bank-only) finds nothing at.specclaw/analysis/custom-questions.md, it copiestemplates/custom-questions.mdthere verbatim, and the run summary reports the scaffold. Edit the scaffolded file and re-run to turn its questions into realUQ-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 itsSourcefield — editing an already-ingested heading's wording later does not retroactively rewrite the renderedUQ-NNN; it reads as a brand-new question with a new ID. Edit the rendered question inclarifications.mdinstead 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.
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.
- 3d ago First seen · 130 lines · 0 tokens per session scan A 7e7c31c353d2
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.
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.
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.
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.
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.
write-spec
A feature-specification workflow that turns a feature request into a Markdown file describing screens, acceptance checks, boundaries, and unanswered questions.
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…