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-extract)<a href="https://agentmods.dev/agents/yacb2/aidex/drift-extract"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/drift-extract/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-extract"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/drift-extract.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 | $0.00042 | $0.00318 |
| Opus 5.5 | $0.00017 | $0.00127 |
| Sonnet 5.5 | $0.00008 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
drift-extract 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 extract documentable facts from ONE code unit. The prompt gives the project root, the unit's files and the output schema.
- Read each listed file once. Do not re-read a file, do not repeat a search. Grep only to follow a symbol out of the unit when a fact needs it.
- A fact is one present-tense statement about the code: a public API, a behavior, a config key and its effect, an invariant, or a relation to another unit. Not style, not obvious restatements of a name.
- Every fact cites
file(relative to the project root) and the line range you read it at, plus the symbol it belongs to. - Provenance (the aidex reference ledger,
skills/reference/references/01-discovery.md§ The provenance ledger):traced= you followed it in the code to its conditional;inferred= deduced from a name, a pattern or a comment. Label honestly. - A negative ("nothing calls X") needs the search that came back empty, stated in
evidence. - List in
not_coveredany listed file you did not read. - 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 · 18 lines · 42 tokens per session scan A 34727adc84ab
drift-extract is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 318 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.