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 agentmods add commands/juanmarchetto/agent-skills/arch-diffgit clone --depth 1 https://github.com/JuanMarchetto/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/commands/juanmarchetto/agent-skills/arch-diff)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/arch-diff"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/arch-diff.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00448 |
| Opus 5 | $0.00010 | $0.00224 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
arch-diff 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 4d 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
/arch-diff -- Quick Drift Summary
You are the Architecture Reviewer skill's quick-check mode. The user has triggered /arch-diff for a fast summary of architecture drift without a full detailed report.
Instructions
Step 1: Find Architecture Documentation
Same discovery as /review-arch -- scan for ARCHITECTURE.md, docs/architecture.md, ADR files, DESIGN.md, etc.
If no docs found:
No architecture documentation found. Use /arch-init to generate one.
Stop here.
Step 2: Fast Scan
Perform a lightweight scan focusing on:
- Module inventory: List documented modules vs actual top-level directories
- Boundary spot-checks: Sample cross-module imports (check 3-5 key boundaries, not all)
- Technology check: Compare documented tech stack to actual
package.json/ config files - Naming check: Compare documented paths to actual directory names
Skip deep analysis of responsibility drift, pattern drift, and scale drift. Speed over thoroughness.
Step 3: Produce Summary
Output in this compact format:
Architecture Drift -- <project-name>
Docs: <list of docs found>
Alignment: ~P% (estimated)
Critical: C items
Warning: W items
Info: I items
Top issues:
[CRITICAL] <one-line summary>
[WARNING] <one-line summary>
[WARNING] <one-line summary>
...
Run /review-arch for the full report.
Rules
- Maximum 30 seconds of analysis -- keep it fast
- Show at most 5 top issues (most severe first)
- The alignment score is an estimate (append "~" to indicate approximation)
- Each issue gets ONE line, no details
- Always end with the
/review-archprompt for users who want more - If everything looks aligned, say so: "No drift detected. Code matches architecture docs."
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.
- 4d ago First seen · 64 lines · 19 tokens per session scan A 7c4b3eb0c12b
arch-diff is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 448 once invoked, about $0.0001 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 commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
unicli-search
Search any supported website or platform using Uni-CLI.
toon
A lightweight data format designed to minimize token usage when passing structured data to LLMs.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
design-qa
Agent-driven design QA — walk the running app, judge design/UX, and drop a Comment-Mode comment on every issue (visible to the human as pins). Then read the session back and fix everything in bulk. Optional focus argument steers the pass.