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 psenger/ai-agent-skills --skill arch-lensgit clone --depth 1 https://github.com/psenger/ai-agent-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/psenger/ai-agent-skills/arch-lens)<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/arch-lens"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/arch-lens/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/psenger/ai-agent-skills/arch-lens"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/arch-lens.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 | $0.00180 | $0.00835 |
| Opus 5 | $0.00090 | $0.00417 |
| Sonnet 5 | $0.00036 | $0.00167 |
| Haiku 4.5 | $0.00018 | $0.00084 |
Grade A, and why
arch-lens 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arch Lens
Seven-step interactive architectural review. An Explore sub-agent navigates the codebase the way a developer would — the confusion, file-bouncing, and untestable seams it encounters are the findings. No checklists, no rigid heuristics.
Deep module: small interface surface hiding a large, self-contained implementation. Lets callers test at the boundary. Lets AI agents reason without reading internals.
Quick start
- If a path argument is given, scope to that directory; otherwise whole repo
- Load
${CLAUDE_SKILL_DIR}/references/WORKFLOW.md— full step-by-step instructions - Load
${CLAUDE_SKILL_DIR}/references/DETECTION-PATTERNS.md - Load
${CLAUDE_SKILL_DIR}/references/INTERFACE-DESIGN.md - Load
${CLAUDE_SKILL_DIR}/references/RFC-FILE-FORMAT.md - Execute the seven steps in WORKFLOW.md
Workflows
| Step | What happens | Requires user input |
|---|---|---|
| 1. Explore | Spawn Explore sub-agent; navigate organically; record friction | — |
| 2. Candidates | Synthesise friction into clusters; present max 8 with full context | — |
| 3. Pick | User selects a cluster and directs the angle | wait |
| 4. Frame | Problem statement, dependency category, blast radius, test boundary today | — |
| 5. Design | Spawn 3–4 parallel sub-agents with competing interface designs | — |
| 6. Choose | User picks interface or accepts recommendation | wait |
| 7. RFC file | Write arch-rfcs-YYYY-MM-DD.md to project root |
— |
Full prompt text, cluster format, and step detail: see WORKFLOW.md.
Behavioural rules
- Explore agent friction observations are primary evidence — never override with static analysis
- Never propose interface designs before Step 5
- Never advance past Steps 3 or 6 without a user response
- Every RFC must include exact
file:linereferences and a before/after illustration - Name every dependency category explicitly — it determines the testing strategy
- Rank clusters: testability impact first, then cognitive load, then interface stability
What ships with it
4 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 · 67 lines · 180 tokens per session scan A 3df5dcc42d3b
arch-lens is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 180 tokens to every session and 835 once invoked, about $0.0009 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".