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 Jarroslav/agentic-os --skill code-review-orchestratorgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/code-review-orchestrator)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/code-review-orchestrator"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/code-review-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.02774 |
| Opus 5 | $0.00076 | $0.01387 |
| Sonnet 5 | $0.00030 | $0.00555 |
| Haiku 4.5 | $0.00015 | $0.00277 |
Grade A, and why
code-review-orchestrator 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 6d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review-orchestrator
Replace a single-pass review with a multi-lens orchestration. Materialize the
diff, gather project context, fan out three independent review lenses as
subagents, adjudicate standards and security against project guides, triage the
merged findings, and write exactly one verdict JSON. That file is the whole
hand-off: gate-arbiter reads it back and records the outcome.
Blast radius: R1. The only file this skill writes is the verdict report. No source files. No broad test suites. No end-of-turn — control returns inline to
gate-arbiter.
Contract
| Field | Value |
|---|---|
| Gate ids | code-review.final, code-review.check |
Output (final) |
<run_dir>/code-review-final.json |
Output (check) |
<run_dir>/code-review-check.json |
| Diff reconstruction | git diff <diff_base> -- . ':(exclude)package-lock.json' |
| Finding IDs | CR-001, CR-002, … ; check-round new id = max(existing CR number) + 1 |
| Verdict fields | decision (approve|request-changes), confidence (low|medium|high), risk_flags, business_review[], standards_review[], findings[], rationale, finding_status (check round only) |
finding_status values |
resolved, unresolved, superseded |
| triage buckets | decision_needed, patch, defer, dismiss |
| severity enum | critical | major (no minor) |
| risk_flags examples | security, breaking-change, public-api |
Each findings[] entry carries a stable ID + a triage bucket + a severity.
decisions.jsonl is written by gate-arbiter, never by this skill.
Inputs
gate_id, original_task, artifacts (ArtifactRefs), prior_verdict
(required on code-review.check — full verdict object OR readable ArtifactRef),
memory_brief, run_dir (effectively required; safe-fail if absent or
unwritable). Story path pattern: docs/stories/<story>.md.
ArtifactRef shape: {"path": ..., "summary": ..., "signature": ...}. Keys:
story, spec (<run_dir>/design.md), git_workflow, code_quality,
security, prior_verdict (<run_dir>/code-review-final.json). Acceptance
artifacts resolvable under run_dir: design.md, requirements.md, the story
file.
What ships with it
7 files 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.
- 6d ago First seen · 206 lines · 151 tokens per session scan A edba5331e81d
code-review-orchestrator is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 2,774 once invoked, about $0.0008 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
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.