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 zstevovich/claude-apd --skill apd-auditgit clone --depth 1 https://github.com/zstevovich/claude-apdWrote 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/zstevovich/claude-apd/apd-audit)<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-audit"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-audit/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/zstevovich/claude-apd/apd-audit"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-audit.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 | $0.00109 | $0.02694 |
| Opus 5 | $0.00055 | $0.01347 |
| Sonnet 5 | $0.00022 | $0.00539 |
| Haiku 4.5 | $0.00011 | $0.00269 |
Grade A, and why
apd-audit 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 10d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APD Project Audit (Codex)
Qualitative review of how APD is configured in the project — content quality, not just file existence. Pairs with
apd:apd_doctor()MCP tool (mechanical checks).
When to use / When to skip
Use when:
- First session after
apd cdx init— confirm everything is correct - After manually editing
.apd/agents/,AGENTS.md, or.codex/config.toml - When the pipeline behaves unexpectedly
- When
apd:apd_doctor()passes but something "feels off" - Before handing the project to another developer
Skip when:
apd:apd_doctor()itself is failing — fix those mechanical issues first- You only need a yes/no health check —
apd:apd_doctor()is faster - Mid-pipeline — audit is for between cycles, not during
What This Checks (apd:apd_doctor Does NOT)
| apd:apd_doctor | apd-audit |
|---|---|
| Files exist? | Content correct and complete? |
| TOML valid? | Hook config actually wires to live scripts? |
| Agents have scope? | Scope paths match the project layout? |
| Pipeline runs? | Pipeline output matches the expected format? |
| Mechanical ✓/✗ | Qualitative review |
Process
1. Run apd:apd_doctor first
apd:apd_doctor()
If it reports errors → fix those first. This skill builds on top of
apd:apd_doctor, not replaces it.
2. Agent quality
For each agent in .apd/agents/*.md:
Roles that must EXIST — check presence before quality:
code-reviewer— missing → the reviewer advance BLOCKsadversarial-reviewer— missing → the reviewer advance BLOCKs (adversarial-agent-missing). Until v7.0 its absence silently disabled the whole adversarial layer, so a project that has been running "clean" without this file was running without the layer. On Codex that layer is the ONLY independent review the pipeline has — supervision is inert here.
Frontmatter check:
scope:list — paths actually exist in the repo? A writable role with no scope in either the YAML key or theguard-scopehook command fails CLOSED atapd:apd_guard_write(v6.37)model:(if present) — the gpt-* namespace.MODEL_PROFILEis CC-only and inert under Codex, so a Claude model name in a Codex project's config is never applied —apd doctorwarns about exactly thiseffort:(if present) — buildersxhigh, reviewersmaxmemory:—noneonadversarial-reviewer(decontextualization contract); flagging it for a missingmemory: projectinverts what makes the role worth dispatching
What ships with it
6 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.
- 10d ago First seen · 229 lines · 109 tokens per session scan A 4b579085c0e9
apd-audit is a skill published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 2,694 once invoked, about $0.0005 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.