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 robzilla1738/roberts-skills --skill autoreviewgit clone --depth 1 https://github.com/robzilla1738/roberts-skillsWrote 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/robzilla1738/roberts-skills/autoreview)<a href="https://agentmods.dev/skills/robzilla1738/roberts-skills/autoreview"><img src="https://agentmods.dev/badge/skills/robzilla1738/roberts-skills/autoreview/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/robzilla1738/roberts-skills/autoreview"><img src="https://agentmods.dev/badge/skills/robzilla1738/roberts-skills/autoreview.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 | $0.00048 | $0.00686 |
| Opus 5 | $0.00024 | $0.00343 |
| Sonnet 5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
autoreview 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Autoreview Session Changes for Production Quality
Purpose
Before considering the task complete, review all changes made in this session and bring them up to production-quality, industry-standard implementation.
This skill is a hard acceptance gate. The work is not done until this review is complete and any discovered issues are fixed properly.
Instructions
Review every file, decision, and implementation change made during this session.
Do not leave behind tech debt, shortcuts, brittle logic, temporary fixes, TODOs, dead code, duplicated logic, unnecessary complexity, or bandaids.
If any shortcut was taken, replace it with the correct long-term implementation before finishing.
Review Checklist
-
Correctness
- Verify the implementation fully satisfies the user request.
- Check edge cases, error handling, empty states, invalid inputs, and failure paths.
- Confirm there are no hidden regressions.
-
Code Quality
- Remove duplicated, dead, unused, or overly clever code.
- Simplify unnecessarily complex logic.
- Use clear names, consistent patterns, and idiomatic structure.
- Keep concerns separated and avoid mixing unrelated responsibilities.
-
Architecture
- Ensure the solution fits the existing project architecture.
- Avoid one-off hacks that bypass established patterns.
- Refactor properly instead of patching around poor structure.
- Do not introduce unnecessary dependencies or abstractions.
-
Maintainability
- Remove temporary comments, TODOs, console logs, debug code, and stale branches.
- Make the implementation easy for another engineer to understand and extend.
- Ensure future changes will not require working around this solution.
-
Security and Reliability
- Validate inputs where appropriate.
- Avoid unsafe assumptions.
- Ensure secrets, credentials, private data, and environment-specific values are not exposed.
- Handle failures gracefully.
-
Testing and Verification
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.
- 9d ago First seen · 95 lines · 48 tokens per session scan A 7f78912e5b3e
autoreview is a skill published in the GitHub repository robzilla1738/roberts-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 686 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pr-review
Review one or all open pull requests in saadeghi/daisyui with read-only GitHub data and isolated base-versus-PR checks. Use when Codex must verify a PR, find concrete regressions, decide whether it is safe to merge, and write a concise report under tmp/pr/.
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
ss-lint
Quick automated lint — detects common design system violations in seconds.
ss-review
Review UI code for design system compliance, accessibility, and best practices.
code-review
Run a thorough self-review pass on the most recent change.
component-api-validator
Audit component APIs for consistency, breaking changes, TypeScript coverage, and contract compliance across a component library. Trigger when someone says: component prop review, verify component types are exported, component API audit, check our component interfaces, are our props consistent, API consistency check…