Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jamie-BitFlight/claude_skills/plugin install dhWrote 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/jamie-bitflight/claude_skills/code-review-architecture)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/code-review-architecture"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-architecture/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/jamie-bitflight/claude_skills/code-review-architecture"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-architecture.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 | $0.00216 | $0.07786 |
| Opus 5 | $0.00108 | $0.03893 |
| Sonnet 5 | $0.00043 | $0.01557 |
| Haiku 4.5 | $0.00022 | $0.00779 |
Grade B, and why
code-review-architecture scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Hook event configs | `**/hooks.json`, `**/.claude/settings.json` | `hook-config` | How it starts
The opening of the file, as written. The whole thing — 655 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Audit — Module Dependency Graph
Generates a Mermaid module-dependency graph with severity color-coding from import/include analysis of the project source. Registers the result as a codebase-analysis artifact.
When to Invoke
Invoke when:
- A task explicitly asks for an architecture review, dependency graph, or coupling analysis
- Circular dependencies need to be detected and visualized
- Module-level coupling must be communicated visually to stakeholders
- Running as part of a broader code review that requires structural analysis
Do NOT invoke for:
- Line-level code quality findings — use
dh:code-review-python,dh:code-review-typescript, etc. - Test quality analysis (out of scope for this skill)
SOP (Architecture Audit)
Step 0: Determine Scope
Auto-detect the analysis scope before touching any source files. Use the first of the following that yields a non-empty file set:
git diff --cached --name-only— files staged for commitgit diff --name-only— unstaged working-tree changesgit diff main...HEAD --name-only(ormaster...HEAD) — PR-level changes; try both base branch names- Entire project tree — fall back when none of the above yields files (e.g., no git history or clean working tree)
Record the detected scope explicitly. It will appear at the top of every output report (e.g., **Scope:** Full project tree — 360 Python files or **Scope:** PR diff — 12 files across 3 modules).
When scope is a diff subset (cases 1–3), still build the full dependency graph (Steps 1–4) but highlight only nodes that appear in the diff set. Do not silently discard the broader graph — cross-boundary edges from diff nodes to stable nodes are the most important coupling signals.
Step 1: Discover Source Modules
1a. Probe for AST / knowledge-graph tools
Before falling back to Glob, check whether a richer indexing skill is available in the current session. Try each probe in order and stop at the first success:
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.
- 5d ago First seen · 655 lines · 216 tokens per session scan B 8599dd7d45e7
code-review-architecture is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed yesterday), licensed MIT. It adds 216 tokens to every session and 7,786 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…