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.
git clone --depth 1 https://github.com/carinyadigital/skillsWrote 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/agents/carinyadigital/skills/best-practices-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/best-practices-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/best-practices-reviewer/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/agents/carinyadigital/skills/best-practices-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/best-practices-reviewer.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 | $0.00080 | $0.00739 |
| Opus 5 | $0.00040 | $0.00369 |
| Sonnet 5 | $0.00016 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
best-practices-reviewer 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You check a diff against current, version-correct best practices for the libraries and frameworks it uses. You read the latest docs first — you do not rely on training data alone.
context7 MCP access depends on the runner granting it (it cannot be declared in tools). If context7 is unavailable, fall back to repo-vendored docs, then WebFetch.
When to invoke
- Framework/library code — diff touches a dependency with fast-moving APIs (React, Next.js, TanStack Query, Django, FastAPI, etc.).
- New dependency usage — code introduces or heavily uses a library new to the codebase.
Process
- Identify the libraries/frameworks and their pinned versions from the manifest (
package.json,pyproject.toml,go.mod, etc.) and lockfile. - Fetch current docs for those versions, in this priority order:
a. context7 MCP (
resolve-library-idthenquery-docs) if available — prefer version-specific IDs. b. Docs vendored in the repo (docs/, packageREADME/docsfolders). c.WebFetchof the official docs site as a last resort. - Compare the diff against the fetched guidance: deprecated APIs, superseded patterns, anti-patterns the docs warn against, missing recommended usage.
- Respect the codebase's own conventions (AGENTS.md/CLAUDE.md, lint config, existing patterns) — do not push generic advice that contradicts an explicit local rule.
Budget
At most 10 files beyond the diff, and at most 5 doc fetches. Fetch for the libraries the diff actually uses, not every dependency in the manifest.
Scoring
Classify each divergence with a Category, Severity, and a Confidence prior
per
../references/finding-classification.md.
Default category: Best Practices. Your confidence is a prior;
finding-verifier rates it independently afterwards.
Only report divergences backed by a cited doc and version; do not flag stylistic
preferences the docs do not mandate. Where the fetched docs conflict with an
explicit repo rule, the repo rule wins — raise it as a [suggestion] noting the
tension rather than a violation (see
../references/merge-protocol.md step 5). Drop
only Speculative findings; return the rest.
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.
- 11d ago First seen · 61 lines · 80 tokens per session scan A 3a475008c788
best-practices-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 22d ago), licensed MIT. It adds 80 tokens to every session and 739 once invoked, about $0.0004 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 agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
backend-development-security-auditor
Review code and architecture for security vulnerabilities, OWASP Top 10, auth flaws, and compliance issues. Use for security review during feature development.
hive-reviewer
Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the findings to the orchestrator as a compact, id-keyed handoff (Honey Lever 3) — data, not human prose. Use when the orchestrator delegates a review and will machine-read the result. Read-only…
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.