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 bostonaholic/team --skill reviewing-codegit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/reviewing-code)<a href="https://agentmods.dev/skills/bostonaholic/team/reviewing-code"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/reviewing-code/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/bostonaholic/team/reviewing-code"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/reviewing-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Agent Snooping · line 30 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 36 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 56 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 80 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00023 | $0.00816 |
| Opus 5 | $0.00012 | $0.00408 |
| Sonnet 5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
reviewing-code 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing Code
Review with fresh context. The generator never evaluates or fixes its output. Reviewers have
read-only tools and permissionMode: plan (principle-generator-evaluator, principle-least-privilege).
Read references/review-manual.md.
Call the Skill tool with writing-prose and apply Self-lint before returning the report.
Report Format
Emit every heading below in order. Use Code Reviewer tokens from Verdict Criteria first. Relay the full report unchanged (principle-skip-loudly).
**Verdict: <✅ APPROVE | ❌ REQUEST CHANGES | 💬 COMMENT>**
### Summary
<Two to five sentences: scope and verdict reason.>
### Findings
<Conventional Comments with `file:line`, or exactly "No findings.">
### Checks
<Every done criterion and each command/result.>
### Refuted by verification
<Refuted findings, exactly "Nothing refuted.", or "Not run: <reason>.">
### Cross-model disposition
<Per `skills/cross-model-review/SKILL.md`, or "Not run: <reason>.">
Gate Types and Severity Tiers
Call the Skill tool with review-severity-tiers; it owns gates, tiers, auto-fix, consult, and aggregation.
Findings use skills/conventional-comments/SKILL.md; UX uses Working/Broken/Could Improve.
Verdict Criteria
Security Reviewer
PASS unless CRITICAL or HIGH exists; either causes FAIL. MEDIUM/LOW findings are reported but do not block.
Verifier
PASS only when format, lint, typecheck, build, and test pass. Any failure returns to IMPLEMENT.
Code Reviewer
✅ APPROVE: done criteria met, no blockers, tests pass. ❌ REQUEST CHANGES: a Blocking issue; return to IMPLEMENT. 💬 COMMENT: only non-blocking suggestions.
Test-quality flags. Call the Skill tool with test-style. One change-detector, mock-chain,
overbroad equality, test logic, method-named test, or opaque helper is suggestion:;
repetition across tests is issue:.
Flaky-test red flags (always blocking). When a test outcome depends on a
nondeterministic input, the first occurrence is issue (blocking). The catalog
lives only in skills/test-style/SKILL.md.
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.
- 4d ago Changed · -195 lines · -42 tokens per session 0eccfd1267cd
- 6d ago First seen · 276 lines · 65 tokens per session scan A 1c4185eb4375
reviewing-code is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 816 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 2026-09-03.
Other skills, from other repositories
codebase-sync
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
code-review-pipeline
Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.
plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
code-review-patterns
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
code-review-orchestration
6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.