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 appleweiping/WEIPING_WIKI --skill auto-review-loopgit clone --depth 1 https://github.com/appleweiping/WEIPING_WIKIWrote 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/appleweiping/weiping_wiki/auto-review-loop)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/auto-review-loop"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/auto-review-loop.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00805 |
| Opus 5 | $0.00028 | $0.00402 |
| Sonnet 5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
auto-review-loop 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review Loop
Simulate a hostile peer review. Iterate until the paper would survive top-venue reviewers.
Decision Gate
Before running:
- Paper draft exists (
paper/main.texcompiles) -
paper/CLAIM_MAP.mdexists - Experiment audit passed
Phase 1 — Structured Review (Codex as Reviewer 1)
Invoke Codex with the paper and this rubric using an explicit context pack through agentmemory signals/actions, or by handing the same context to the current Codex session:
Review Rubric (score 1-10 each)
| Dimension | Question |
|---|---|
| Novelty | Is this a genuine new insight, or incremental/stitching? |
| Clarity | Can a PhD student in the field understand the method in one read? |
| Soundness | Are claims supported by evidence? Any logical gaps? |
| Significance | Would this change how people think about the problem? |
| Reproducibility | Could someone reimplement from the paper alone? |
| Completeness | Are baselines comprehensive? Ablations sufficient? |
| Presentation | Figures clear? Tables readable? Writing concise? |
Required Output
## Review Summary
Overall: Accept / Weak Accept / Borderline / Weak Reject / Reject
## Strengths (3-5 bullets)
## Weaknesses (3-5 bullets, ranked by severity)
## Questions for Authors
## Minor Issues (typos, formatting, unclear sentences)
## Scores
Novelty: X/10
Clarity: X/10
...
Phase 2 — Kill Argument (Codex as Adversary)
Ask Codex to write the strongest possible rejection argument:
- "Why should this paper be rejected?"
- "What's the fatal flaw?"
- "What experiment would disprove the main claim?"
If the kill argument is valid and unanswerable → the paper needs fundamental revision.
Phase 3 — Sonnet Quick Scan (Reviewer 2)
Invoke Sonnet for a fast second opinion using agentmemory signals/actions or an explicit current-session handoff:
- Focus on: clarity, missing references, presentation issues
- Sonnet is cost-effective for surface-level review
Phase 4 — Author Response & Revision
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.
- 8d ago First seen · 96 lines · 56 tokens per session scan A 32c373d78463
auto-review-loop is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 805 once invoked, about $0.0003 per session on Opus 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
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…