Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yonatangross/orchestkit/plugin install orkWrote 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/yonatangross/orchestkit/review-pr)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/review-pr"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/review-pr.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 | $0.00069 | $0.06351 |
| Opus 5 | $0.00034 | $0.03175 |
| Sonnet 5 | $0.00014 | $0.01270 |
| Haiku 4.5 | $0.00007 | $0.00635 |
Grade A, and why
review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR
Deep code review using 6-7 parallel specialized agents.
Quick Start
/ork:review-pr 123
/ork:review-pr feature-branch
Opus 5: Parallel agents use native adaptive thinking for deeper analysis. Complexity-aware routing matches agent model to review difficulty.
Argument Resolution
The PR number or branch is passed as the skill argument. Resolve it immediately:
PR_NUMBER = "$ARGUMENTS[0]" # e.g., "123" or "feature-branch"
# If no argument provided, check environment
if not PR_NUMBER:
PR_NUMBER = os.environ.get("ORCHESTKIT_PR_URL", "").split("/")[-1]
# If still empty, detect from current branch
if not PR_NUMBER:
PR_NUMBER = "$(gh pr view --json number -q .number 2>/dev/null)"
Use PR_NUMBER consistently in all subsequent commands and agent prompts.
STEP 0: Verify User Intent with AskUserQuestion
BEFORE creating tasks, clarify review focus:
AskUserQuestion(
questions=[{
"question": "What type of review do you need?",
"header": "Focus",
"options": [
{"label": "Full review (Recommended)", "description": "Security + code quality + tests + architecture"},
{"label": "Security focus", "description": "Prioritize security vulnerabilities"},
{"label": "Performance focus", "description": "Focus on performance implications"},
{"label": "Quick review", "description": "High-level review, skip deep analysis"}
],
"multiSelect": false
}]
)
Based on answer, adjust workflow:
- Full review: All 6-7 parallel agents
- Security focus: Prioritize security-auditor, reduce other agents
- Performance focus: Add frontend-performance-engineer agent
- Quick review: Single code-quality-reviewer agent only
"Ultra" mode → defer to claude ultrareview (CC 2.1.120+, #1542)
If the user asks for an "ultra" / "deep" / "thorough" review and the host is on CC ≥ 2.1.120, defer to the native subcommand instead of re-implementing the multi-agent loop in skill instructions:
What ships with it
17 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.
- references/adversarial-refutation.md 3.4 KB
- references/cross-model-output.schema.json 2.2 KB
- references/cross-model-refuter.md 12 KB
- references/memory-persistence.md 1.3 KB
- references/orchestration-mode-selection.md 837 B
- references/review-report-template.md 894 B
- references/review-template.md 2.4 KB
- references/task-metrics-template.md 531 B
- references/ultrareview-gate.md 3.2 KB
- references/validation-commands.md 1.1 KB
- rubric.json 5.6 KB
- rules/_sections.md 518 B
- rules/agent-prompts-agent-teams.md 6.0 KB
- rules/agent-prompts-task-tool.md 9.7 KB
- rules/ai-code-review-agent.md 1.2 KB
- scripts/verdict_writeback.py 9.1 KB runs code
- test-cases.json 3.0 KB
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.
- today Changed a259921af31a
- 2d ago First seen · 492 lines · 69 tokens per session scan A 1ebcb33d53c5
review-pr is a skill published in the GitHub repository yonatangross/orchestkit (231 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 6,351 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 2026-09-05.
Other skills, from other repositories
review
Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate. Produces review.md with decision points. Requires developer approval before $ship can proceed.
stage-coach
Consume CocoSentinel per-stage external coach requests and produce stage quality scores.
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.
code-reviewer
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
test-writing
Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.