Borrowing it
Nothing to install: this file belongs to Undertone0809/rudder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Undertone0809/rudder/main/.agents/skills/maintainer/agent-work-reviewer-maintainer/SKILL.mdgit clone --depth 1 https://github.com/Undertone0809/rudderWrote 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/undertone0809/rudder/agent-work-reviewer-maintainer)<a href="https://agentmods.dev/skills/undertone0809/rudder/agent-work-reviewer-maintainer"><img src="https://agentmods.dev/badge/skills/undertone0809/rudder/agent-work-reviewer-maintainer/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/undertone0809/rudder/agent-work-reviewer-maintainer"><img src="https://agentmods.dev/badge/skills/undertone0809/rudder/agent-work-reviewer-maintainer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.03007 |
| Opus 5.5 | $0.00024 | $0.01203 |
| Sonnet 5.5 | $0.00012 | $0.00601 |
| Haiku 4.5 | $0.00006 | $0.00301 |
Grade A, and why
agent-work-reviewer-maintainer 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 13d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Work Reviewer Maintainer
Judge whether the work solved the right problem, produced a coherent Rudder experience, and earned the claimed level of acceptance. This is a read-only review role, not an implementation or black-box-verifier role.
Proportional Scope
Follow AGENTS.md section 9.1. Review the requested artifact and risks; do not
turn a docs or skill review into a product-release workflow. For instructions,
evaluate realistic decisions and conflicting rules. Runtime/data identity and
black-box product evidence apply only to claims that depend on them.
A short requirement-to-evidence mapping is sufficient for a bounded task. Use a formal packet or state matrix when multiple requirements, corrections, workflow states, or integration risks make it useful. Do not manufacture missing packet fields for facts that cannot affect the requested outcome.
Role Boundary
- Inspect the request, diff, relevant code, tests, screenshots, and running surface when they materially affect judgment.
- Do not edit files, stage, commit, push, or fix findings during the review.
- Treat inherited parent history and implementer claims as author-claimed evidence until this reviewer independently inspects or reruns them.
- Use
product-acceptance-verifier-maintainerfor final black-box acceptance. Reviewer inspection can challenge or refine acceptance criteria, but cannot replace the verifier's terminal verdict when AGENTS.md requires that gate.
Verdicts
Return exactly one reviewer verdict and name its level:
accept: no blocking product, implementation, evidence, or handoff gap remains for this level.needs more evidence: the available artifact or proof is insufficient for a trustworthy judgment.reject: the work solves the wrong problem, creates a blocking regression, or requires a different product or implementation direction.
Use accept with clearly non-blocking suggestions when the task is ready.
Do not emit conditional accept: it conflates a pass with an unmet condition.
For older receipts, inspect the actual conditions before deciding applicability.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +10 lines 8b7fac19b251
- 1mo ago Changed fb3bf3c727a4
- 1mo ago Changed · +13 lines · -30 tokens per session fd981b400763
- 2mo ago First seen · 288 lines · 89 tokens per session scan A 89c695932b27
agent-work-reviewer-maintainer is a skill published in the GitHub repository Undertone0809/rudder (294 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 3,007 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 2026-08-30.
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"…
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…
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…