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 agentmods add commands/askwigconsulting/cohort/code-reviewgit clone --depth 1 https://github.com/askwigconsulting/cohortWhat 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 | $0.00019 | $0.00415 |
| Opus 5 | $0.00010 | $0.00208 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
code-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 2d 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.
What it actually says
Invoke the agent-skills:code-review-and-quality skill.
Review the current changes (staged or recent commits) across all five axes:
- Correctness — Does it match the spec? Edge cases handled? Tests adequate?
- Readability — Clear names? Straightforward logic? Well-organized?
- Architecture — Follows existing patterns? Clean boundaries? Right abstraction level?
- Security — Input validated? Secrets safe? Auth checked? (Use security-and-hardening skill)
- Performance — No N+1 queries? No unbounded ops? (Use performance-optimization skill)
Categorize findings as Critical, Important, or Suggestion. Output a structured review with specific file:line references and fix recommendations.
Verdict block
End your output with a fenced ```verdict block — one overall line plus one
line per axis, each pass|fail with a one-line evidence note:
overall: PASS|FAIL
correctness: pass|fail — one-line evidence
readability: pass|fail — one-line evidence
architecture: pass|fail — one-line evidence
security: pass|fail — one-line evidence
performance: pass|fail — one-line evidence
Rules:
overallisFAILif any axis isfail;PASSonly if all five axes pass.- Emit exactly one line per axis, in the order above, even when an axis has no findings (
pass — no issues found). - This fence must be the last fence in your output — it is the only verdict-shaped text a caller should trust. See the office-guide skill's "Verdict blocks" section for the full trust rule.
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.
- 2d ago First seen · 44 lines · 19 tokens per session scan A 214eebaf8878
code-review is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 19 tokens to every session and 415 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.