auditX

A read-only review procedure that tests code changes against stated acceptance criteria. An acceptance criterion is a specific condition the work must meet.

In plain words
What is it for?
Use it for independent evaluator reviews in xflow, focused test runs, failure reporting, and concise PASS, NEEDS_FIX, or UNEVALUABLE results.
Why use it?
It provides evidence about whether the change works without claiming tests passed when they were not run, and identifies blockers when testing is not possible.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/treex-x/workflowx/auditx
Any agent
npx skills add TreeX-X/WorkFlowX --skill auditx
Clone the repo
git clone --depth 1 https://github.com/TreeX-X/WorkFlowX

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00295
Opus 5 $0.00007 $0.00148
Sonnet 5 $0.00003 $0.00059
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash 1baa62a9a43e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditX 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 2d 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.

.claude/skills/auditX/SKILL.md · 33 lines

What it actually says

auditX

Use only when xflow requests an independent evaluatorX review.

Review

  1. Read the review task, Child acceptance criteria, changed files, and relevant diff.
  2. Convert each applicable acceptance criterion into a focused executable test or check.
  3. Run the smallest useful test set.
  4. Record passed tests, failed cases, failure causes, and blocking dependencies.
  5. Inspect code manually only to explain a failed test or a named integration risk; do not perform a full static review by default.

If the project has no runnable test path, report Unevaluable with the reason and the checks attempted. Never claim a test passed unless it was run.

Result Contract

Return a concise Evaluation Result:

  • Status: PASS | NEEDS_FIX | UNEVALUABLE
  • Tests Run: [commands or checks]
  • Passed: [cases]
  • Failed: [case, observed result, likely cause, repair scope, regression risk]
  • Blockers: [dependency or environment issue, or None]

For NEEDS_FIX, keep each failure compact enough for the Main Agent to turn directly into a Repair Packet. Distinguish local defects from cross-Child integration findings when evidence supports it.

evaluatorX is read-only. The Main Agent owns document updates and any follow-up implementation.

Changes

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.

  1. 2d ago First seen · 33 lines · 14 tokens per session scan A 1baa62a9a43e

Subscribe to this mod's changes

auditX is a skill published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 295 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 2026-08-30.