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-bootstrapgit 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-bootstrap)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-bootstrap"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-bootstrap.svg" alt="Measured on agentmods" 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 | $0.00315 | $0.04240 |
| Opus 5 | $0.00158 | $0.02120 |
| Sonnet 5 | $0.00063 | $0.00848 |
| Haiku 4.5 | $0.00032 | $0.00424 |
Grade A, and why
bf-bootstrap 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 yesterday.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-bootstrap
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).
Create the target application's foundation in the new (rebuild) repo. This is the stage that used to be missing, and its absence is what let the first backlog item proposed accidentally inherit responsibility for inventing half the application skeleton — a screen-bearing item quietly shipping as a backend-only slice because nothing else owned the frontend's existence.
The boundary that defines this command: it creates the things every backlog item will stand on, and not one thing any backlog item is for. See The foundation-only boundary below; it is enforced by a gate, not by good intentions.
Read-only side-command with respect to .specclaw/analysis/ and .specclaw/baseline/ — it never writes into either, never touches the legacy repo, and calls no lifecycle skill or script. It is the one brownfield command that writes application source, and it does so exactly once per repo.
Invocation:
/specclaw:bf-bootstrap # scaffold the foundation
/specclaw:bf-bootstrap --adopt # a foundation already exists by hand: smoke + record it, scaffold nothing
/specclaw:bf-bootstrap --not-applicable "<why>" # this repo is not the rebuild target; record that once
Step 0 — --not-applicable (early exit)
Only when the user invoked --not-applicable. This repo is not the rebuild target — record the declaration and stop. Nothing else on this page runs: no collect, no agent, no scaffold, no smoke.
specclaw-bf-bootstrap not-applicable .specclaw \
--reason "<why — the user's own words>" \
--declared-by "<name>, <YYYY-MM-DD>"
Both flags are required and the subcommand refuses the declaration without them. That is deliberate: this declaration switches off /specclaw:propose's target-foundation gate, and an unexplained or unattributable one is indistinguishable from having skipped the foundation by accident — the exact failure the gate exists to catch. Ask the user for their name, and for the reason if the invocation didn't carry one; never supply either yourself.
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.
- yesterday First seen · 159 lines · 0 tokens per session scan A 8ad27f855594
bf-bootstrap is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 2d ago), licensed MIT. It adds 315 tokens to every session and 4,240 once invoked, about $0.0016 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
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-foundation-core
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…