Borrowing it
Nothing to install: this file belongs to TalonT-Org/AutoSkillit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TalonT-Org/AutoSkillit/main/.claude/skills/audit-arch/SKILL.mdgit clone --depth 1 https://github.com/TalonT-Org/AutoSkillitWrote 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/talont-org/autoskillit/audit-arch)<a href="https://agentmods.dev/skills/talont-org/autoskillit/audit-arch"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-arch.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 5.1 | $0.00056 | $0.06022 |
| Opus 5 | $0.00028 | $0.03011 |
| Sonnet 5 | $0.00011 | $0.01204 |
| Haiku 4.5 | $0.00006 | $0.00602 |
Grade A, and why
audit-arch 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 6d 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 — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Audit Skill
Audit the codebase for adherence to architectural standards and rules.
When to Use
- User says "audit arch", "audit architecture", "check architecture"
Critical Constraints
NEVER:
- Modify any source code files
- Update an existing report - always generate new
ALWAYS:
- Use subagents for parallel exploration
- Write report to
{{AUTOSKILLIT_TEMP}}/audit-arch/arch_audit_{YYYY-MM-DD_HHMMSS}.md(relative to the current working directory) - Provide file paths and line numbers
- Categorize by severity (CRITICAL, HIGH, MEDIUM, LOW)
Architectural Principles
Principle 1: Single Source of Truth
Rule: All state reads must come from the authoritative source (database, API, configuration management). File outputs and caches are write-only. Systems never read files back as the primary source of state.
Audit Strategy — 3-Question SSOT Test:
Before flagging any file read as a P1 violation, ask all three questions. All three must be YES to report a violation:
- Two competing authoritative stores? — Are there two (or more) distinct stores that both claim to hold the same piece of state? If there is only one store (e.g., the file IS the authority, memory is just the working copy), there is no SSOT violation.
- Can they diverge during NORMAL operation? — Could the two stores hold different values during steady-state operation (not crash/restart/migration)? Startup bootstrapping that only runs once on a cold start is NOT "normal operation" for this test.
- Architecturally sound reconciliation? — If the two stores diverge, which one wins? If the reconciliation strategy makes the file the authoritative source (file is read first, or file "wins" by default), that IS a violation regardless of documentation. Only a strategy where the canonical store (database, API, config manager) takes precedence is compliant. A comment saying "file always wins" is not a reconciliation strategy — it is a description of the violation.
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.
- 6d ago First seen · 447 lines · 56 tokens per session scan A 7913a27f2fe4
audit-arch is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 6,022 once invoked, about $0.0003 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
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…
a0-review-plugin
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
laravel-audit-dsa
Run a read-only, orchestrated audit of a Laravel codebase for data structures, state representation, algorithms, and ownership. Use when asked for a DSA audit, subsystem inventory, or Aaron-style bounded agent audit.
laravel-audit
Perform a deep, structured, evidence-based audit of a Laravel application and produce actionable findings backed by concrete project evidence. Use when asked to audit, review, assess, or evaluate an existing Laravel codebase.
代码审查员
专业代码审查专家,提供建设性、可操作的反馈,聚焦正确性、可维护性、安全性和性能,而非代码风格偏好。.