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 jh941213/codex-lattice --skill evalgit clone --depth 1 https://github.com/jh941213/codex-latticeWrote 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/jh941213/codex-lattice/eval)<a href="https://agentmods.dev/skills/jh941213/codex-lattice/eval"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/eval/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/jh941213/codex-lattice/eval"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/eval.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 | $0.00075 | $0.00560 |
| Opus 5.5 | $0.00030 | $0.00224 |
| Sonnet 5.5 | $0.00015 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
eval 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 1mo 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
코드 Eval (독립 평가)
Generator(구현자)와 분리된 Evaluator 에이전트를 스폰하여 산출물을 독립 평가합니다.
실행 프로세스
Step 1: Evaluator 에이전트 사용
Codex custom agent evaluator를 사용한다. 서브에이전트 사용은 사용자가 명시했거나 현재 Codex 실행 지침상 허용될 때만 수행한다.
요청 프롬프트:
현재 변경사항을 독립 평가하라.
4축(기능 정확성/코드 품질/단순성/사용성&보안) 100점 만점.
증거는 git diff, 테스트/빌드 출력, 파일 참조만 인정한다.
결과를 PASS / CONDITIONAL / FAIL로 판정하고 필요한 fix-forward 루프를 제안하라.
Step 2: 결과 확인
Evaluator가 완료되면 EVAL_REPORT.md를 읽고 사용자에게 요약 보고:
Eval 결과: [PASS/CONDITIONAL/FAIL] — [N]/100점
기능 정확성: [N]/40 | 코드 품질: [N]/25
독창성: [N]/20 | 사용성&보안: [N]/15
[수정 필요 항목 요약]
Step 3: CONDITIONAL/FAIL 시
수정 필요 항목을 구체적으로 안내하고, 수정 후 재평가할지 질문. 재평가 시 동일 기준 적용 (최대 5라운드).
pass@k 멱등성 테스트 (선택)
동일 프롬프트로 k회 실행하여 품질 일관성을 측정:
# k=3 실행 예시
for i in 1 2 3; do
/eval 실행 → 점수 기록
done
# 3회 모두 85+ → 멱등성 확보
# 점수 분산 > 15점 → 불안정 (하네스 조정 필요)
수준의 멱등성: 정확히 같은 코드가 아니라 같은 품질 수준이 유지되는지 측정.
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.
- 1mo ago First seen · 58 lines · 75 tokens per session scan A 2028aa11cc6e
eval is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 560 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…