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 magnus919/hermes-profiles --skill review-methodologygit clone --depth 1 https://github.com/magnus919/hermes-profilesWrote 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/magnus919/hermes-profiles/review-methodology)<a href="https://agentmods.dev/skills/magnus919/hermes-profiles/review-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/review-methodology/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/magnus919/hermes-profiles/review-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/review-methodology.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 | $0.00041 | $0.00519 |
| Opus 5 | $0.00020 | $0.00260 |
| Sonnet 5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
review-methodology 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.
What it actually says
Review Methodology
Professional review standards for code, security, architecture, and swarm output verification.
Review Types
| Type | Reference | When to load |
|---|---|---|
| Code review | references/code-review-standards.md |
Reviewing a PR or diff — 9 dimensions from Google's engineering practices plus project-specific conventions |
| Security review | references/security-review.md |
Auditing for vulnerabilities — threat modeling, vulnerability classes, dependency analysis, supply chain |
| Architectural review | references/architectural-review.md |
Evaluating design decisions — coupling/cohesion, scalability, data flow, abstraction boundaries |
| Swarm gate | references/swarm-verification.md |
Evaluating swarm worker outputs — passing or blocking the kanban verifier gate |
Templates
| Template | When to use |
|---|---|
templates/code-review-response.md |
Writing a PR review with findings organized by severity |
templates/security-finding.md |
Documenting a security vulnerability with reproduction steps |
templates/swarm-verdict.md |
Passing or blocking the kanban verifier gate with evidence |
The Review Mindset
Every review follows the same arc, regardless of type:
- Understand intent — What is the change trying to achieve? Read the description, issue, or brief first.
- Assess correctness — Does it achieve its stated goal? Start here before considering style or elegance.
- Assess quality — Is it well-constructed for its purpose? Complexity, maintainability, test coverage.
- Assess risk — What could go wrong? Edge cases, security, regressions, operational impact.
- Communicate — Clear findings, severity levels, actionable next steps. Not personal, not dismissive.
Never skip to quality or style before understanding intent and correctness. A well-styled solution to the wrong problem is still wrong.
What ships with it
7 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.
- 11d ago First seen · 45 lines · 41 tokens per session scan A 21505a2e7fe1
review-methodology is a skill published in the GitHub repository magnus919/hermes-profiles (169 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 519 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…