Borrowing it
Nothing to install: this file belongs to sageox/ox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sageox/ox/main/.claude/skills/review-incoming-pr/SKILL.mdgit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/review-incoming-pr)<a href="https://agentmods.dev/skills/sageox/ox/review-incoming-pr"><img src="https://agentmods.dev/badge/skills/sageox/ox/review-incoming-pr/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/sageox/ox/review-incoming-pr"><img src="https://agentmods.dev/badge/skills/sageox/ox/review-incoming-pr.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 | $0.00247 | $0.04973 |
| Opus 5 | $0.00123 | $0.02486 |
| Sonnet 5 | $0.00049 | $0.00995 |
| Haiku 4.5 | $0.00025 | $0.00497 |
Grade A, and why
review-incoming-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 2d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-incoming-pr
You are the maintainer reviewing someone else's PR. Your job is a merge decision backed by an actual security + quality pass, not a rubber stamp and not a re-run of what CodeRabbit/Greptile already said. Two goals, in order: (1) protect customers and our own systems from a bad merge; (2) keep the contributor moving — small gaps we can fix ourselves should not block their PR.
The whole pipeline:
flowchart LR
P[abort session<br/>review runs private] --> G[collect.sh<br/>context]
G --> R[risk tier]
R --> S[security pass]
R --> Q[quality pass]
S --> T[triage bot threads]
Q --> T
T --> D{decision}
D -->|data-loss / authz / secret / RCE| B[BLOCK + escalate]
D -->|correctness / design / large| C[request changes]
D -->|correct & safe, only small polish| F[approve + fast-follow PR]
D -->|clean| A[approve + auto-merge]
B --> N[INTERNAL next steps<br/>never posted to PR]
C --> N
F --> N
A --> N
Step 0 — privacy fence: discard this session's recording FIRST
Before you read a line of the diff, abort the active ox session recording. Reviewing a PR means enumerating how it could hurt customers or our own systems — our threat model, and where we're soft. That enumeration is exactly what must not leak into the ledger and sync to the team. So the whole review runs unrecorded.
- Invoke
/ox-session-abort(it resolves the active agent + session). Under the hood that isox agent <id> session abort— irreversible: it permanently discards the current session and uploads nothing to the ledger. Confirm with the human before aborting. Non-interactively, abort requires--force:ox agent <id> session abort --force # drop --force in a terminal to get the y/N prompt - After abort the recording no longer exists: do not add a
SageOx-Sessiontrailer to any commit or PR you open for this review. - Escape hatch — if you're mid-other-work in this session and need the pre-review part
kept,
/ox-session-pausenow and/ox-session-resumewhen the review is fully done instead; that excises only the review span. The default here is abort.
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.
- 2d ago Changed · -1 lines 0d3011a69d3c
- 12d ago First seen · 320 lines · 247 tokens per session scan A 0e1b539cb592
review-incoming-pr is a skill published in the GitHub repository sageox/ox (53 stars, last pushed today), licensed MIT. It adds 247 tokens to every session and 4,973 once invoked, about $0.0012 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
code-review-checklist
Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
plan-eng-review
Engineering plan review. Reviews a plan document for architecture, code quality, test coverage, and performance before implementation begins. Produces a coverage diagram, failure modes map, and parallelization strategy. Use when asked to "review this plan", "eng review", or "architecture review".
review
Pre-merge code review — the single canonical review of a change before it lands. Covers BOTH diff safety/structure (SQL safety, LLM trust-boundary violations, conditional side effects) AND engineering quality (architecture fit, edge cases, test coverage, performance). Use when asked to "review this PR", "code review"…
audit
Use when the user asks to audit this repo, run the engineering audit, run a practice audit, or check the codebase against the engineering-audit rules pack. Drives the engineering-audit MCP server's tools through a full audit run and produces a self-contained HTML report.