Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Lykhoyda/ask-llm/plugin install ask-llmWrote 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/lykhoyda/ask-llm/ask-llm-codex-verify)<a href="https://agentmods.dev/skills/lykhoyda/ask-llm/ask-llm-codex-verify"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-codex-verify/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/lykhoyda/ask-llm/ask-llm-codex-verify"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-codex-verify.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 | $0.00099 | $0.01553 |
| Opus 5.5 | $0.00040 | $0.00621 |
| Sonnet 5.5 | $0.00020 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
ask-llm-codex-verify 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 14d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portable contract
Capture the prior assistant message verbatim, decompose it into atomic claims, and verify those claims against actual repository state with a read-only Codex consultation where useful. This is claim verification, not issue hunting. Preserve the Report block, five-grade confidence ladder, parser fallback, and explicit unverifiable state.
Host adapters
Pi adapter
Apply the portable contract above inline and call native ask-codex for focused claim checks. Do not claim an isolated verifier context.
Other hosts adapter
Codex, Cursor Agent, Antigravity, Grok Build, Gemini CLI and OpenCode get this skill from their skills folder, not from a plugin. Apply the portable contract above inline and use the Codex call from ../ask-llm-review/transport.md for focused claim checks: model: "gpt-6-astra", reasoningEffort: "high", sandbox: "read-only". Do not claim an isolated verifier context.
Claude Code adapter
The existing detailed workflow below is the Claude Code adapter. Its Agent, MCP, hook, CLAUDE_PLUGIN_ROOT, and AskUserQuestion mechanics apply only on Claude Code; they do not override the Pi adapter above.
Codex Claim Verification
Prove or disprove what the assistant agent claims to have done in the current turn, independently. This is a trust check, not an issue hunt — separate from /codex-review.
Why this is separate from /codex-review
/codex-reviewlooks for new bugs in the diff (issue hunt)./codex-verifyproves the assistant's claims against actual state (trust verification).
A single tool would dilute both contracts. The verifier is structurally narrowed by design: it does not propose fixes, does not list issues outside the assistant's claims, does not drift into "while I'm here let me also...". That narrowness is the feature — it forces every "verified" verdict to be backed by a deterministic tool output.
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.
- 14d ago First seen · 115 lines · 99 tokens per session scan A 797023d15c56
ask-llm-codex-verify is a skill published in the GitHub repository Lykhoyda/ask-llm (18 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 1,553 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
debug-workflow
Run the Maestro debugging workflow for investigation-heavy tasks.
perf-check
Run a Maestro-style performance assessment for hotspots, regressions, and optimization planning.
second-opinion
Get an independent review of the current change from a different model family (GPT via Codex, Copilot or Cursor; Gemini via Antigravity) through agent-intern, then check each finding against the code and reconcile it with your own view. Use before merging a risky diff, when stuck on a bug, or when the user asks for a…
cli-audit-code
Audit code quality with weighted scoring across 12 dimensions (naming, complexity, module design, DRY, errors, security, tests, architecture). Detects named anti-patterns (Fowler/Mantyla taxonomy). Use when reviewing code quality, auditing clean code compliance, checking for code smells, or saying 'audit code', 'code…
review
Audit code in scope against your architectural rules; report drift (dead code, SoC, monolith, missing-pattern, principle, comment-drift, naming-quality) with propose-confirm per fix; route misses to /capture. Triggers: /review [path | --since | --vault], "review this", "audit the architecture", "check for drift".…
using-ccproxy-inspector
Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic. Covers running CLI tools through the reverse proxy or permissive WireGuard namespace capture path, checking namespace status and doctor output, inspecting flows with client-vs-forwarded request comparison…