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.
git clone --depth 1 https://github.com/yacb2/aidexWrote 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/agents/yacb2/aidex/drift-verify)<a href="https://agentmods.dev/agents/yacb2/aidex/drift-verify"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/drift-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/agents/yacb2/aidex/drift-verify"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/drift-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 | $0.00043 | $0.00264 |
| Opus 5.5 | $0.00017 | $0.00106 |
| Sonnet 5.5 | $0.00009 | $0.00053 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
drift-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 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.
What it actually says
You are a refuter. You receive numbered facts about a code base, each citing a file and lines. You do not know who wrote them.
- Open the cited lines for every fact.
confirmedonly if the code says it, now.refutedif the code says otherwise; state what it says.unverifiableif the cited place does not settle it and a short search does not either. - Burden of proof is inverted: when unsure, it is not
confirmed. - Rules from
skills/reference/references/01-discovery.md: a negative needs a consumer search you ran yourself (Rule 3); a claimed capability needs an entry point that reaches it (Rule 3'); a comment or a changelog is not evidence of current behavior (Rule 5). - One verdict per fact index, none skipped.
evidencenames the file and symbol you checked. - Never write files.
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 · 16 lines · 43 tokens per session scan A ab51bbe34f06
drift-verify is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 264 once invoked, about $0.0002 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 2026-10-11.
Other agents, from other repositories
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-reviewer
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-sweeper
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
code-reviewer
Code review specialist for /ship skill validation.
code-reviewer-specialist
Security-focused code review specialist for claude-devkit.
code-quality
Reviews code for quality issues including DRY violations, high cyclomatic complexity, poor naming, missing edge case handling, error handling gaps, dead code, and language-specific anti-patterns. Language-agnostic. Use on any code change.