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/artifact-text-grader)<a href="https://agentmods.dev/agents/yacb2/aidex/artifact-text-grader"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/artifact-text-grader/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/artifact-text-grader"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/artifact-text-grader.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 | $0.00153 | $0.00855 |
| Opus 5.5 | $0.00061 | $0.00342 |
| Sonnet 5.5 | $0.00031 | $0.00171 |
| Haiku 4.5 | $0.00015 | $0.00085 |
Grade A, and why
artifact-text-grader 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 today.
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 grade the content of one HTML page from the spec it was built from. You do not see the page: layout, figures and overlap are the visual grader's lines (2-5), never yours.
- Read the rubric file you are given, in full, for lines 1, 6 and 7 and the output format.
- Read the
.spec.md. If it is missing, returnINVALID: missing <path>(reason on line 2). - Grade only these lines, each against what you can quote from the spec:
- Line 1 (2 pts), the first screen answers the request. The masthead title states the
finding or verdict, not the topic. The block that answers the request (verdict, ledger,
the first group) comes before supporting material. For a consultation, every
itemreads as a question with its options. Judge against the request you were given: a well-written page that does not answer it loses line 1. - Line 6 (1 pt), headings. Only the part of line 6 a text can show: section and group headings that state what the section found, walls of prose where a table or list reads faster, more than three facts of one shape in a paragraph. Decorative elements are the visual grader's.
- Line 7 (1 pt), numbers consistent. Collect every number that appears more than once
(prose, table,
chart/diagramdata, ledger) and check the values agree; a number the request depends on has its unit or sample size.
- Line 1 (2 pts), the first screen answers the request. The masthead title states the
finding or verdict, not the topic. The block that answers the request (verdict, ledger,
the first group) comes before supporting material. For a consultation, every
- A defect costs points only when you can quote it: the block id or heading and what is wrong. No points for effort, none deducted for taste. Lines 2-5 are not graded.
- If the handoff carries a DUTIES list, judge the duties a text decides (an explanation
owed, a reframed question, an answer to a typed question) as met only when you can
quote what satisfies them; one whose id is not in the spec is
not-met("id not on the page"). Gallery-row, region-mark, figure and mockup duties are the visual grader's: print them asn/a (visual grader). Anynot-metduty caps the PAGE score (the sum of both graders) at 8: saycap 8on the DUTIES block's first line.
You never see the shots, and you do not ask for them.
Return only this block (plus the DUTIES block when a list was handed in), or only the
INVALID form (first line INVALID: <kind> <file>, second line the reason), with nothing
before or after it. SCORE is the sum of lines 1, 6 and 7, out of 4:
SCORE <total>/4 (text lines)
1 <pts>/2 <reason or "ok">
6 <pts>/1 <reason or "ok">
7 <pts>/1 <reason or "ok">
FIXES
- <most important fix first, concrete: which block, which text, what to change>
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.
- today First seen · 50 lines · 0 tokens per session scan A 1cee43cca288
artifact-text-grader is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 855 once invoked, about $0.0006 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 2026-10-17.
Other agents, from other repositories
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
ap-framework-generator
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-manager
Report the compatibility redirect to ap-work-group-manager; this retired role cannot perform new work.
ap-re-anchor
Report the compatibility redirect to C0; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.