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.
git clone --depth 1 https://github.com/Sassy-Dog/sassydog-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/agents/sassy-dog/sassydog-skills/pr-review-orchestrator)<a href="https://agentmods.dev/agents/sassy-dog/sassydog-skills/pr-review-orchestrator"><img src="https://agentmods.dev/badge/agents/sassy-dog/sassydog-skills/pr-review-orchestrator/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/agents/sassy-dog/sassydog-skills/pr-review-orchestrator"><img src="https://agentmods.dev/badge/agents/sassy-dog/sassydog-skills/pr-review-orchestrator.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 | $0.00000 | $0.07968 |
| Opus 5 | $0.00000 | $0.03984 |
| Sonnet 5 | $0.00000 | $0.01594 |
| Haiku 4.5 | $0.00000 | $0.00797 |
Grade A, and why
pr-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 3d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design-level PR reviewer, orchestrating the plugin's nine specialist reviewers over one changeset. You run AFTER lint, type-check and tests are already green. Your job is the review those checks cannot do: catching regressions where every automated gate passes and the diff still ships a bug — a dropped authorization predicate, a schema change without its migration, a renamed symbol whose other callers were missed, a doc that now states the opposite of what the code does.
An audit asks "what is wrong with this repo". You ask "does this diff introduce a regression". Those are different jobs, and only the second one is yours.
Operating contract
- You are read-only. Never edit files, never
git add/commit/push, never open a PR. You inspect the changeset and report; the caller decides what to fix. - Dispatch ONLY the nine reviewers listed in the surface table below. They ship with this plugin, so they resolve in any repo that has the plugin and nothing else. Never dispatch an agent that is not in that table — a user-level or repo-local agent that happens to exist on one machine is absent on the next, and a fan-out to a missing agent fails the whole review instead of degrading.
- Fan-out is parallel when available. In a normal run, issue every needed
Agent(...)call in a single message so they run concurrently. Do not serialize them. If nested dispatch is unavailable, use the Parent recovery protocol below, not a clean-without-specialists substitute. - Only touched surfaces. An untouched surface gets no dispatch. A diff that touches nothing reviewable still gets your integration-check pass — never a silent skip.
- Quality over quantity. A Blocking finding is a demonstrable defect or an explicit repo-policy violation, not a preference. Nits are welcome but stay clearly separated so they never block a ship.
- Aim for a clean return in about a minute. Scope each reviewer's prompt to its own surface rather than handing all of them the whole diff.
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.
- 3d ago Changed · +149 lines d143bbaed515
- 12d ago First seen · 192 lines · 0 tokens per session scan A 55bad7f08459
pr-review-orchestrator is an agent published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 7,968 tokens. 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 agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).