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 lakpriya1s/agent-rack --skill review-handlinggit clone --depth 1 https://github.com/lakpriya1s/agent-rackWrote 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/lakpriya1s/agent-rack/review-handling)<a href="https://agentmods.dev/skills/lakpriya1s/agent-rack/review-handling"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/review-handling/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/lakpriya1s/agent-rack/review-handling"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/review-handling.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 | $0.00038 | $0.00386 |
| Opus 5 | $0.00019 | $0.00193 |
| Sonnet 5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
review-handling 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 11d 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
Presenting agent_review output
agent_review (and background review sessions surfaced via agent_session_status's review
field) return a structured object, not free text. Handle it consistently:
- Present
verdictandsummaryfirst, thenfindingsordered byseverity(critical → high → medium → low), thennext_steps. - Use the
file/line_start/line_endfields exactly as returned.0means whole-file, deleted-file, or architectural — not a real line number; don't imply otherwise. - If
parseError: true, the sub-agent's reply couldn't be validated against the review schema. Say so explicitly and show therawtext rather than inventing a verdict from it. - If
verdict: "approve"andsummaryis exactly"Nothing to review.", that means agent-rack short-circuited before even spawning an agent (no diff existed) — say there was nothing to review, don't imply a review actually ran. - Read-only means read-only: agent_review never modifies files, regardless of
adversarial.
Critical: never auto-fix
After presenting findings, stop. Do not make any code changes, apply patches, or treat findings
as an implicit task list. Explicitly ask the user which findings, if any, they want addressed
before touching a single file — even when a fix looks obvious or trivial. This applies whether
the review ran via /agent-rack:review or was triggered as part of a larger task.
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.
- 11d ago First seen · 29 lines · 38 tokens per session scan A 1b79ec429399
review-handling is a skill published in the GitHub repository lakpriya1s/agent-rack (1 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 386 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
agy-delegate
Delegate coding tasks to the Google Antigravity CLI (agy) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
cao-workflow
Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…
aidlc-portfolio
Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…
cao-plugin
Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when…
cao-provider
Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.