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-pr-reviewgit 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-pr-review)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-pr-review"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-pr-review/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-pr-review"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 115 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Excessive Agency · line 285 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00065 | $0.04209 |
| Opus 5 | $0.00032 | $0.02105 |
| Sonnet 5 | $0.00013 | $0.00842 |
| Haiku 4.5 | $0.00006 | $0.00421 |
Grade A, and why
synthesis-pr-review 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.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis PR Review
A pull request in a synthesis-coded project is not just "does the code work?" It is "does this change make the system better without making it worse?" This skill defines how to evaluate that.
Where This Fits
Eight related engineering skills cover different scopes and lifecycle phases:
| Skill | Scope | When to use |
|---|---|---|
| preplan | Architecture-decision locking for a ticket | Before any plan exists — lock the load-bearing design choices via Q&A |
| code-planning | Approach selection for a task | Before writing code — evaluate alternatives, pick the best approach |
| implementation-integrity | Self-verification of a single implementation | After completing work — "Is my code genuinely complete?" |
| code-audit | 10-dimension quality scan of a diff | After implementation — systematic quality measurement |
| preflight | Branch readiness gate | Before creating a PR — tests, types, audit, commit hygiene |
| review-triage | PR queue prioritization | Before starting review — which PR to review next |
| pr-review (this one) | Delta review of a single change | Every PR, before peer approval or lead integration |
| code-integration | Integration workflow (adopt-and-adapt pattern, quality gates) | When merging contributor work into main |
| codebase-review | Full codebase audit (16 categories, tiered) | Periodic health check or major milestone |
PR review is the most frequent review skill. It happens on every change. The synthesis-code-audit skill provides systematic quality data that feeds into reviews; this skill provides the judgment-based evaluation and communication. The quality gates from synthesis-code-integration apply here, but this skill operationalizes them as specific review steps.
The Delta Review Mindset
A PR review is a delta review — you are evaluating a change against the current state of the codebase, not evaluating the codebase itself.
Key questions:
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.
- 11d ago First seen · 346 lines · 65 tokens per session scan A f35e298dc149
synthesis-pr-review is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 4,209 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 2026-08-30.
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…