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 ashermahonin/agentic-skills --skill architecture-reviewgit clone --depth 1 https://github.com/ashermahonin/agentic-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/skills/ashermahonin/agentic-skills/architecture-review)<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/architecture-review"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/architecture-review/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/ashermahonin/agentic-skills/architecture-review"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/architecture-review.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 | $0.00465 |
| Opus 5 | $0.00040 | $0.00233 |
| Sonnet 5 | $0.00016 | $0.00093 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
architecture-review 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 12d 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
Architecture Review
Purpose
Turn requirements and current-state evidence into a system shape that can be implemented, tested, operated, and changed. Prefer clarity and tradeoffs over ornamental diagrams.
Inputs
- Gather requirements, quality scenarios, current-state evidence, and constraints.
- Name the architecture decision that matters most.
- Identify boundaries: user/system, service/service, data/API, sync/async, build/runtime, trust zones.
- Decide what must be documented as an ADR.
Decision process
- Draft the system context first, then containers, then components only where detail changes decisions.
- Map runtime scenarios for critical user and failure paths.
- Define data ownership, API contracts, integration contracts, and deployment assumptions.
- Review crosscutting concerns: auth, secrets, observability, errors, retries, rate limits, privacy, migration, rollback, and operations.
- Write tradeoffs explicitly, including what is intentionally not solved.
- Refuse implementation handoff until risky decisions have owners and validation paths.
Decision boundaries
- Use Context7 MCP for current library, framework, platform, API, CLI, and configuration documentation whenever the task depends on external technology behavior.
Decision record
- System context
- Container and component views
- Runtime scenarios
- Deployment view
- Data model and API contracts
- ADR candidates or decisions
Ready when
- Architecture must answer how the system changes safely, not only how it works when happy.
- Do not draw a component unless it affects ownership, contract, or risk.
- Call out irreversible or expensive decisions.
- Tie architecture back to requirements and quality scenarios.
Handoff
Hand off boundaries, contracts, ADRs, validation expectations, and unresolved risks to decomposition.
References
references/architecture-artifacts.md: Use this to decide which architecture artifacts are required.
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.
- 12d ago First seen · 55 lines · 80 tokens per session scan A cb9e73aed404
architecture-review is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 19d ago), licensed MIT. It adds 80 tokens to every session and 465 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 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…