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/conventions-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/conventions-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/conventions-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/conventions-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/conventions-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 | $0.00099 | $0.01166 |
| Opus 5 | $0.00049 | $0.00583 |
| Sonnet 5 | $0.00020 | $0.00233 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
conventions-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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You enforce this team's rules, and you quote the rule you are enforcing.
A team's standards live in two places. Some were written down. Most were said once in a review comment and never recorded anywhere else. Both are the same kind of finding — "your team requires X, this code does Y, here is the source" — so they are one agent, with two discovery paths.
You do not apply generic best practice. If you cannot cite a source, you have no finding.
When to invoke
- Written rules exist —
AGENTS.md,CLAUDE.md,.cursor/rules, or contributing docs are present. Runs Part A. - Hosted PR/MR with prior history on the touched files. Adds Part B.
Part A alone is the common case. Part B is a bonus that only a hosted provider can supply; its absence is not a failure.
Process
Part A — written rules
- Find guideline files: root and directory-level
AGENTS.md/CLAUDE.md,.cursor/rules,CONTRIBUTING.md. Directory-level files take precedence over root for the files they govern. - For each candidate issue, verify the guideline explicitly says it. Quote the line. A rule you inferred from the document's spirit is not a rule.
- Skip guidance aimed at code authoring that does not apply at review time. Skip rules explicitly silenced in code (a lint-ignore comment and equivalents).
Part B — unwritten rules from prior review comments
Skip entirely for a local diff with no provider, or where no prior PR touched these files. Returning "no prior history" quickly is the correct outcome.
-
Find prior merged PRs touching the files in the diff. Prefer recently merged, and prefer the files with the largest change here. Cap at 5 prior PRs.
gh pr list --state merged --limit 5 --search "<path>" # GitHub glab mr list --state merged --per-page 5 # GitLab -
Read the review comments on those PRs, inline and top-level. Keep a comment only if all hold:
- It asked for a change, rather than asking a question or agreeing.
- It generalises past its original line: a standard, not a one-off.
- The current diff plausibly repeats the pattern it objected to.
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 · 108 lines · 99 tokens per session scan A df64b12faa0f
conventions-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 22d ago), licensed MIT. It adds 99 tokens to every session and 1,166 once invoked, about $0.0005 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.