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 mblode/agent-skills --skill ax-auditgit clone --depth 1 https://github.com/mblode/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/skills/mblode/agent-skills/ax-audit)<a href="https://agentmods.dev/skills/mblode/agent-skills/ax-audit"><img src="https://agentmods.dev/badge/skills/mblode/agent-skills/ax-audit.svg" alt="Measured on agentmods" 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 100 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 | $0.00075 | $0.02735 |
| Opus 5 | $0.00037 | $0.01367 |
| Sonnet 5 | $0.00015 | $0.00547 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade A, and why
ax-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ax-audit — 88% identical, 107 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AX Audit
Feature-level reviewer for apps where an agent acts for the user. One question: does it earn trust, and where does it break?
- IS: rules-based audit of agentic surfaces (chat, tool execution, config, dashboards) across architecture (
rules-arch/) and trust (rules-ax/), ending in a ship-readiness verdict plus an AX Relationship Summary. - IS NOT: traditional frontend UX (use
ui-designAudit mode); developer-facing API, CLI, or type ergonomics (usedx-audit); agent instruction files (useagents-md); what the product should do before it exists (useproduct-design).
No agentic features in scope? Stop. AX rules against forms and lists are noise.
Contents
- Audit workflow
- Two rule layers
- Tiers and verdict
- AX Relationship Summary
- Reference files
- Gotchas
- Audit self-check
- Related skills
Audit workflow
AX Audit progress:
- [ ] Step 1: Scope, via the diff against the PR base merge-base (PR mode) or explicit path (full sweep)
- [ ] Step 2: Detect agentic features per references/feature-playbooks.md
- [ ] Step 3: Run each detected feature's playbook in order, plus the diff-wide checks (PR mode only)
- [ ] Step 4: For each check, load the rule file and follow its detection recipe
- [ ] Step 5: Tier each finding per references/ship-readiness.md (rule override table wins)
- [ ] Step 6: Render verdict + findings + AX Relationship Summary per references/output-format.md
- [ ] Step 7: Run the audit self-check and report its evidence counts
PR-mode scope is the diff plus the tool definitions and orchestrator it touches. Findings in untouched files belong in a full sweep, not this verdict. Playbook annotations are a scan copy; the rule file is authoritative. parity-orphan-ui-action runs on every PR-mode audit and never in a full sweep, where there is no diff for it to read.
What ships with it
40 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.
- evals/evals.json 1.4 KB
- references/agent-native-principles.md 6.7 KB
- references/ax-evolution-curve.md 5.3 KB
- references/evaluation-scenarios.md 6.8 KB
- references/feature-playbooks.md 9.6 KB
- references/framework-signals.md 8.3 KB
- references/invisible-interface.md 3.0 KB
- references/output-format.md 5.2 KB
- references/ship-readiness.md 5.6 KB
- rules-arch/_sections.md 5.2 KB
- rules-arch/_template.md 2.6 KB
- rules-arch/comm-no-approval-gate.md 5.9 KB
- rules-arch/comm-no-completion-signal.md 3.6 KB
- rules-arch/comm-no-progress-visibility.md 4.3 KB
- rules-arch/context-no-checkpoint-resume.md 3.0 KB
- rules-arch/context-no-injection.md 2.6 KB
- rules-arch/context-starvation.md 2.9 KB
- rules-arch/granularity-static-api-mapping.md 3.9 KB
- rules-arch/granularity-workflow-shaped-tool.md 3.6 KB
- rules-arch/parity-crud-incomplete.md 2.7 KB
- rules-arch/parity-no-tool-parity.md 3.3 KB
- rules-arch/parity-orphan-ui-action.md 3.0 KB
- rules-arch/parity-unstructured-tool-output.md 6.0 KB
- rules-ax/_sections.md 4.3 KB
- rules-ax/_template.md 2.6 KB
- rules-ax/comm-no-generative-momentum.md 2.6 KB
- rules-ax/comm-no-intent-handshake.md 3.5 KB
- rules-ax/comm-no-progress-signal.md 3.5 KB
- rules-ax/comm-unrequested-action-no-consent.md 6.5 KB
- rules-ax/context-memory-not-visible.md 3.0 KB
- rules-ax/context-no-adaptive-canvas.md 3.2 KB
- rules-ax/context-under-contextual.md 2.9 KB
- rules-ax/control-no-approval-gate.md 4.2 KB
- rules-ax/control-no-escape-hatch.md 3.3 KB
- rules-ax/control-over-conversational.md 2.5 KB
- rules-ax/control-thin-approval-payload.md 6.0 KB
- rules-ax/trust-no-confidence-cues.md 3.0 KB
- rules-ax/trust-no-escalation-path.md 2.8 KB
- rules-ax/trust-no-uncertainty-markers.md 2.7 KB
- rules-ax/trust-undisclosed-access-scope.md 5.5 KB
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.
- 2d ago Changed · -51 tokens per session 99056c8b0743
- 8d ago First seen · 129 lines · 126 tokens per session scan A fcb90542c539
ax-audit is a skill published in the GitHub repository mblode/agent-skills (105 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,735 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves GRAPHPROJECT, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
verify-findings
Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). Reads verifymanifest.json (written by stage22bverifyprepare), spawns one falsify-oriented verifier Task per toverify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel…
report-manager
Manage and refine vision-powers reports: list, open, delete, search, and refine sections. Use when asked to list, open, delete, search, or update generated HTML reports.
claw-mux
Control cmux terminal topology and I/O — send commands to panes, read output, split layouts, monitor logs, orchestrate multi-pane workflows. Requires cmux environment.
fetch-sitemap
Extract URLs from an XML sitemap with optional regex filtering.
cmux-markdown
Open markdown files in a cmux formatted viewer panel with live reload. Use when you need to display plans, documentation, or notes alongside the terminal with rich rendering (headings, code blocks, tables, lists). Requires cmux environment ($CMUXWORKSPACEID).