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-rebuild-plangit 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-rebuild-plan)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-rebuild-plan"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-rebuild-plan/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-rebuild-plan"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-rebuild-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 53 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00017 | $0.05947 |
| Opus 5.5 | $0.00007 | $0.02379 |
| Sonnet 5.5 | $0.00003 | $0.01189 |
| Haiku 4.5 | $0.00002 | $0.00595 |
Grade A, and why
bf-rebuild-plan 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 24d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-rebuild-plan
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 four analysis documents — plus, when present, decisions.md, clarifications.md, and the baseline outputs (manifest.json/scenarios.md) — into a living, ID-stable rebuild backlog. Read-only side-command — no specclaw-validate-change call, no <change> involved, matching the analyze/architecture/domain/clarify/baseline pattern.
Determine the invocation mode from the user's message: refresh mode if it contains --refresh, default mode otherwise. Additionally, if the message contains --module MOD-###, this is a module-scoped run: pass that flag through to both collect and render, unchanged.
Step 1 — Collect
mkdir -p .specclaw/analysis/.collect
specclaw-bf-rebuild-collect collect .specclaw [--refresh] [--module MOD-###] > .specclaw/analysis/.collect/rebuild-plan.json
Pass --refresh only in refresh mode, and --module MOD-### only if the user named a module. Check the exit status before spawning anything below, and never hand the agent a path to a half-written file. This single step:
- Checks that all five
.specclaw/analysis/*.mddocuments exist — the four analysis documents plusmodule-map.md, which declares theMOD-###modules every backlog item is grouped under. If it exits non-zero for this reason, surface its stderr message to the user verbatim and stop — it names exactly which document(s) are missing and which command produces each (module-map.mdcomes from/specclaw-bf:bf-domain). Don't retry, don't attempt a partial backlog from partial input, and never invent a grouping to work around a missing map. - Fails if
--modulenames no active module in the map, listing the ones that do exist. A withdrawn module cannot be planned — its id stays claimed as a tombstone. - If
.specclaw/analysis/rebuild-backlog.mdalready exists and--refreshwas not passed, it exits non-zero with a refusal message — surface that message verbatim and stop. Do not delete or archive the file yourself; tell the user to re-run with--refresh, or to archive/delete it manually first if they genuinely want a from-scratch run. - Otherwise emits one JSON object to stdout: the module roster from
module-map.md(each module's id, name, active/withdrawn status,DR-###rules, and dependencies) together with the map's ownPROPOSED/CONFIRMEDstatus and this run'smodule_scope; the five documents' paths/line counts; which optional inputs are present (decisions.md,clarifications.md,.specclaw/baseline/manifest.json,.specclaw/baseline/scenarios.md) with their resolved paths; everyclarifications.mdquestion'sid/type/blocking/answered/rules/items(ID-level facts only, no prose); whichCQ-###ids have a recorded decision; thescenarios.mdroster andmanifest.jsonfixtures (id/rules/item); whether a "No Legacy Behaviour Exists" section is present; and — in refresh mode — every existingBL-###item'sid/title/depends_on/rules/status/prior Gate/Verification. It also reports the next freeBL-###id.
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.
- 24d ago Changed · +17 tokens per session 998da56b93fe
- 1mo ago Changed 21e84e6fe870
- 1mo ago Changed · +1 lines feb228bf96a2
- 2mo ago First seen · 150 lines · 0 tokens per session scan A 3b78748d4558
bf-rebuild-plan is a skill published in the GitHub repository chan4lk/specclaw (14 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 5,947 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 2026-09-05.
bf-rebuild-plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bf-rebuild-planchan4lk/specclaw | Skill | 14 | 3d ago | MIT | A | 17 | Claude Code |
| backloga-lottes/aSPARK | Skill | 25 | 2d ago | MIT | A | 94 | Claude Code |
| backend-developerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 94 | Claude Code |
| javaolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 136 | Claude Code |
| secops-engineerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 161 | Claude Code |
| sqlolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 94 | Claude Code |
| e2e-testerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 72 | Claude Code |