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 liza-mas/liza --skill software-architecture-reviewgit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/software-architecture-review)<a href="https://agentmods.dev/skills/liza-mas/liza/software-architecture-review"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/software-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/liza-mas/liza/software-architecture-review"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/software-architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 665 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00009 | $0.06940 |
| Opus 5 | $0.00005 | $0.03470 |
| Sonnet 5 | $0.00002 | $0.01388 |
| Haiku 4.5 | $0.00001 | $0.00694 |
Grade A, and why
software-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 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 — 674 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REVIEW_FILE = specs/architecture/architecture-review.md
Recommended Tools: Make sure you've read ~/§BRAND_GLOBAL_DIRNAME§/AGENT_TOOLS.md list_directory_tree and codebase_search (fast and token-efficient semantic search) may be specifically useful.
Architecture is about trade-offs, not truths. Raise questions, suggest directions, avoid astronautics.
Invoked for: implementation planning, code review (P3 supplement), or explicit architectural evaluation.
Process
Discovery → Analysis → Recommendations
Templates anchor cognition. Complete Phase 1 before Phase 2. The skill is a lens to apply to what you found, not slots to fill.
Modes
| Mode | When | Scope |
|---|---|---|
| Full Review | Explicit architectural evaluation, major implementation planning | All phases, all sections |
| Code Review Supplement | Adding P3 architectural notes to a code review | Targeted analysis of changes only |
| Enrichment | Second+ pass to improve coverage of existing review | Independent analysis → merge → verify → update |
| Enrichment (no lens) | Avoid tunnel vision from lens focus | Same as Enrichment, but unconstrained exploration |
| Adversarial | Break out of convergent attention patterns | Randomized exploration → gap hunting → forced comparisons |
| Adversarial (targeted) | Suspect gaps in specific area | Specific file/component as entry, rest of Adversarial process |
| Adversarial (entry point N) | Force specific exploration pattern | Fixed entry point from table, rest of Adversarial process |
Phase applicability:
| Mode | Phase 1 (Discovery) | Phase 2 (Analysis) | Phase 3 (Recs) | Output |
|---|---|---|---|---|
| Full Review | ✓ Complete | ✓ Complete | ✓ Complete | New REVIEW_FILE |
| Code Review Supplement | — Skip | Targeted (relevant questions only) | — Skip | Inline notes in code review |
| Enrichment | ✓ Fresh (independent) | Update (add to existing) | Update (add to existing) | Revised review file |
| Adversarial | Own process (randomized) | Update (add to existing) | Update (add to existing) | Revised review file |
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 · 674 lines · 9 tokens per session scan A 0ef63f1b1d08
software-architecture-review is a skill published in the GitHub repository liza-mas/liza (384 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9 tokens to every session and 6,940 once invoked, about $0.0000 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
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…