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-prototypegit 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-prototype)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-prototype"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-prototype/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/chan4lk/specclaw/bf-prototype"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-prototype.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 | $0.00020 | $0.02905 |
| Opus 5.5 | $0.00008 | $0.01162 |
| Sonnet 5.5 | $0.00004 | $0.00581 |
| Haiku 4.5 | $0.00002 | $0.00291 |
Grade A, and why
bf-prototype 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-prototype
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).
Run this in the legacy repo, after /specclaw-bf:bf-blueprint.
This stage exists only under REINTERPRET, and under REINTERPRET it is mandatory. A project that decided FAITHFUL, THEME-ONLY, or has not decided SQ-013 at all sees nothing: this command stops with a one-line reason and writes nothing, and every other command behaves exactly as it did before this command existed. Under REINTERPRET the whole new-repo side is locked until this command prints PROTOTYPE: READY — /specclaw-bf:bf-bootstrap will not scaffold and /specclaw:propose will not draft.
What this command is, and is not. It owns the records and the gates: the legacy-screen → prototype-screen map, the permanent PS-### ids, the questions a redesign raises, the approval join, the bash-computed readiness, and the tamper-evident manifest. It does not contain a UI generator and never will. A separate prototype/UI skill — named in config.yaml's prototype.skill — builds the prototype, in the framework and language the project decided.
The prototype is design-acceptance code and is thrown away. It is built in the real target stack so the client approves realistic component behaviour and the production team can read it as a reference. It is never copied to the new repo, never a /specclaw-bf:bf-bootstrap input, and --adopt refuses it by hash. Only the map, the manifest and the screenshots travel.
Determine the mode from the user's message:
| If the message contains | Mode |
|---|---|
--record |
Mode C — hash, join approvals, compute readiness |
--brief-only |
Mode B — brief only; the prototype is built elsewhere |
| neither | Mode A — brief and generate (default) |
Mode A — brief and generate (default)
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.
- 4d ago Changed · +20 tokens per session 88330635491e
- 24d ago First seen · 166 lines · 0 tokens per session scan A 81763e101b2e
bf-prototype is a skill published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,905 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
from-intake
A workflow for reviewing material brought from another workspace and carrying relevant brand evidence into the project's assets. It checks inventories, brand guides, logos, and image sources before anything is used.
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.
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.
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.
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.
loki-mode
An autonomous software factory that knows what it is supposed to deliver, and proves it did. Use when the user says Loki Mode or asks to build, fix or verify software autonomously.