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 alonf/specrew --skill brownfield-bootstrap-safety-reviewgit clone --depth 1 https://github.com/alonf/specrewWrote 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/alonf/specrew/brownfield-bootstrap-safety-review)<a href="https://agentmods.dev/skills/alonf/specrew/brownfield-bootstrap-safety-review"><img src="https://agentmods.dev/badge/skills/alonf/specrew/brownfield-bootstrap-safety-review/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/alonf/specrew/brownfield-bootstrap-safety-review"><img src="https://agentmods.dev/badge/skills/alonf/specrew/brownfield-bootstrap-safety-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00031 | $0.00636 |
| Opus 5 | $0.00015 | $0.00318 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
brownfield-bootstrap-safety-review 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 7d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Use this when reviewing a bootstrap CLI that must merge into an existing workspace without silently mutating conflicting user-owned surfaces.
Patterns
- Judge the slice against the full entrypoint (
specrew init), not the analyzer/helper script alone. - Verify conflict handling happens before any deployment or scaffold step that can touch conflicting role or charter surfaces.
- Treat a target containing only
.gitas greenfield-fresh; treat any additional pre-existing content as populated workspace state that still needs the safety gate. - Treat
-Forceas allowed to skip consent only; it must not suppress brownfield conflict blocking. - Require a persistent dry-run artifact from the entrypoint path when the requirement calls for reviewable safety evidence.
- Require entrypoint-level integration coverage for both the blocked-conflict path and the accepted no-conflict brownfield path.
- Confirm user-facing docs describe the same blocked path, dry-run artifact location, and
-Forceconstraint that the tests and code implement. - In docs review, reject any brownfield quickstart that shows
specrew init -ProjectPath .succeeding on a populated repo unless the code explicitly permits that case; the common safe wording is dry-run first, then-Forcefor genuinely populated workspaces.
Examples
scripts\specrew-init.ps1runs brownfield analysis, writes.specrew\bootstrap-dry-run-{timestamp}.md, and exits 5 on conflicts before deployment.tests\integration\brownfield-conflict-handling.ps1proves dry-run artifact creation, conflict blocking,-Forcenon-bypass, and no-conflict success via the real entrypoint.tests\integration\bootstrap-to-iteration.ps1proves agit initworkspace with only.gitcan bootstrap without-Force.tests\integration\bootstrap-to-iteration.ps1keeps the accepted entrypoint bootstrap flow covered after initialization.
Anti-Patterns
- Accepting a helper script pass while the top-level bootstrap command can still write after detecting conflicts.
- Accepting console-only dry-run summaries when the requirement calls for a reviewable artifact file.
- Treating
.gitmetadata alone as user content that forces-Forceon an otherwise fresh repo. - Treating
-Forceas permission to continue through detected brownfield conflicts. - Relying on isolated helper-script tests without entrypoint coverage of the accepted brownfield path.
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.
- 7d ago First seen · 41 lines · 31 tokens per session scan A d284c7ba7b49
brownfield-bootstrap-safety-review is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 636 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…