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 stefanrossmeier/ai-craftkit --skill cockburn-reviewgit clone --depth 1 https://github.com/stefanrossmeier/ai-craftkitWrote 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/stefanrossmeier/ai-craftkit/cockburn-review)<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/cockburn-review"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/cockburn-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/stefanrossmeier/ai-craftkit/cockburn-review"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/cockburn-review.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 | $0.00036 | $0.03434 |
| Opus 5.5 | $0.00014 | $0.01374 |
| Sonnet 5.5 | $0.00007 | $0.00687 |
| Haiku 4.5 | $0.00004 | $0.00343 |
Grade A, and why
cockburn-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 1mo 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 — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cockburn Review Skill
Command: /cockburn-review
Generate an evidence-based architectural boundary review for the currently opened repository.
The skill inspects the repository, applies the "not my job" and "no need to know" architectural lens, fills the bundled review template, removes unused template sections, and writes the final report to the repository's docs/ folder.
Invocation Model
Use this skill when the user calls:
/cockburn-review
This is a skill invocation, not a shell command. It has no command-line parameters, flags, modes, or options.
If the user adds text around or after the invocation, treat that text as plain-language review guidance. Do not parse it as command syntax.
Examples of plain-language guidance:
- focus on one module or product area
- review the current change set if repository diff information is available
- stress-test the architecture against a named future change
- pay special attention to framework leakage, persistence coupling, or duplicated policy
Do not document or advertise flag-based usage for this skill.
Purpose
/cockburn-review discovers architectural weaknesses by inspecting how responsibilities and knowledge move across repository boundaries.
It asks two core questions:
- Not my job: Is this code doing work that appears to belong to another architectural role?
- No need to know: Does this code know implementation details that should be hidden behind a boundary?
The goal is not to create generic architecture documentation. The goal is to produce a concrete, evidence-based review that helps humans and agents make safer architectural changes.
Required Output File
Generate or update exactly this primary report:
docs/COCKBURN_REVIEW.md
Create docs/ if it does not exist.
Do not place the generated report outside docs/.
Do not modify application source code.
Do not modify unrelated documentation unless the user explicitly asks.
Template Location
Use the bundled template as the conceptual source:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +6 lines · +36 tokens per session 440c23de973e
- 2mo ago First seen · 606 lines · 0 tokens per session scan A fe26e9d04cb5
cockburn-review is a skill published in the GitHub repository stefanrossmeier/ai-craftkit (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 3,434 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 2026-08-31.
cockburn-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cockburn-reviewstefanrossmeier/ai-craftkit | Skill | 5 | 4d ago | Apache-2.0 | A | 36 | Claude Code, Codex |
| architecture-decision-record-maintainer-skillarchitecture-decision-record/architecture-decision-record | Skill | 17k | 8d ago | none | A | 92 | Claude Code, Codex |
| auditEvolveHQ/docflow | Skill | 16 | 15d ago | MIT | A | 141 | Claude Code, Codex |
| adr-compliancezircote-plugins/adr | Skill | 6 | 2mo ago | MIT | A | 56 | Claude Code |
| tech-debtDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 25 | Claude Code |
| solid-principlesdecebals/claude-code-java | Skill | 770 | 8d ago | MIT | A | 73 | Claude Code, Codex |
| architecture-reviewdecebals/claude-code-java | Skill | 770 | 8d ago | MIT | A | 51 | Claude Code, Codex |