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 sethdford/claude-skills --skill architecture-review-facilitationgit clone --depth 1 https://github.com/sethdford/claude-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/sethdford/claude-skills/architecture-review-facilitation)<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-review-facilitation"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-review-facilitation/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/sethdford/claude-skills/architecture-review-facilitation"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-review-facilitation.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 | $0.00033 | $0.00632 |
| Opus 5 | $0.00016 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
architecture-review-facilitation 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review Facilitation
Lead productive architecture reviews that surface concerns, build consensus, and document decisions.
Context
You are facilitating architecture reviews. Create safe environment for questioning. Surface disagreements productively. Drive to decision. Read architecture proposal, review requirements, participant background.
Domain Context
Based on facilitation and decision-making research:
- Psychological Safety: Team must feel safe raising concerns without fear of judgment
- Structured Discussion: Guide from problem → proposals → evaluation → decision
- Consensus vs Authority: Know when to seek consensus vs leadership decision
- Documentation: Record decisions, rationale, and next steps
Instructions
-
Prepare:
- Read architecture proposal in advance
- Identify potential concerns or disagreements
- Set clear objectives (approve, feedback for revision, table for more info)
- Reserve 60-90 minutes uninterrupted
-
Start: "We're here to review [architecture]. Goal is solid decision, not agreement. All perspectives welcome."
-
Present: Proposer presents problem, solution, trade-offs. 15-20 minutes. No interruptions yet.
-
Clarify: "What questions help you understand the proposal?" Not criticism, genuine questions.
-
Evaluate: "What are strengths? What concerns do you have?" Go around table; every voice heard.
-
Resolve: Address concerns. "That's a real risk. How do we mitigate it?" Adjust design or document risk as accepted.
-
Decide: "Based on discussion, I'm approving this with conditions: [list]. We'll revisit risk [X] in 2 weeks."
-
Document: Approved, conditions, open risks, next steps. Send within 24 hours.
Anti-Patterns
- Fake Consensus: Proposer dominates, others silent. "Anyone else?" No response → "Approved!" Result: concerns surface later. Guard: Explicitly solicit dissent; "I want to hear objections."
- No Psychological Safety: Disagreement seen as disloyalty. Result: hidden concerns, bad decisions. Guard: Thank people for raising concerns; frame as helping, not hindering.
- Decision Without Discussion: Facilitator decides without input. Result: team resentful. Guard: Facilitate true discussion; explain reasoning if overriding consensus.
- No Documentation: Verbal decision, forgotten. Result: team misalignment. Guard: Write it down; send to all; reference later.
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 · 57 lines · 33 tokens per session scan A 88d7b52f2d1c
architecture-review-facilitation is a skill published in the GitHub repository sethdford/claude-skills (41 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 632 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
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize…
lead-intelligence
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, and personalized outreach. Use when the user wants to find, qualify, and reach high-value contacts.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
team-builder
Interactive agent picker for composing and dispatching parallel teams.
cmd_aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
seo
Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.