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 synthesisengineering/synthesis-skills --skill synthesis-review-triagegit clone --depth 1 https://github.com/synthesisengineering/synthesis-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/synthesisengineering/synthesis-skills/synthesis-review-triage)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-review-triage"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-review-triage/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/synthesisengineering/synthesis-skills/synthesis-review-triage"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-review-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.02185 |
| Opus 5 | $0.00046 | $0.01092 |
| Sonnet 5 | $0.00018 | $0.00437 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
synthesis-review-triage 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 12d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Review Triage
Review triage decides which PR to review next. It does not evaluate code — that is the job of synthesis-pr-review and synthesis-code-audit. Triage is a routing and scheduling methodology: classify the queue, score each item by urgency, and direct review effort where it has the most impact.
The most common failure in code review is not low-quality reviews — it is reviewing the wrong thing at the wrong time. A team that reviews the newest PR first while a merge-ready PR sits waiting for one more approval is wasting reviewer capacity. Triage prevents this.
Where This Fits
| Skill | Scope | When to use |
|---|---|---|
| review-triage (this one) | PR queue prioritization | Before starting a review session — decide which PR to review next |
| pr-review | Delta review of a single change | Every PR, before peer approval or lead integration |
| code-audit | 10-dimension quality scan of a diff | During review, as systematic input alongside judgment-based evaluation |
Triage is upstream of everything in the review path. Run it before opening any PR.
Queue Classification
Every open PR belongs to exactly one of three categories:
1. Reviewable
PRs that need your review action. This is the working queue — everything you score and prioritize comes from here.
2. Waiting on Author
PRs that are genuinely blocked on the author. Changes were requested or a blocker was raised, and the author has not responded. These are visible for awareness but not actionable by the reviewer.
3. Blocked
PRs held by external factors — labels like "blocked" or "do not merge," dependency on another PR, or infrastructure holds. Shown for awareness, not actionable.
Exclusion Rules
Before scoring, remove PRs that should not be in your queue:
- Self-authored — you do not review your own PRs.
- Drafts — the author has not marked the PR ready for review.
- Already approved by you — your review work is done. This includes dismissed approvals that were positive in nature (contained "LGTM," "looks good," or similar signals with no blockers). A dismissed approval after a force-push does not mean the reviewer's assessment was wrong — it means the platform reset the review state.
- Already reviewed by you with no new code commits — you have seen this code. If the most recent commit on the PR predates your last review, there is nothing new to evaluate.
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.
- 12d ago First seen · 201 lines · 92 tokens per session scan A 2b4ae57c0328
synthesis-review-triage is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 2,185 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…