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 agentmods add skills/evoelsewhere/evoflux/review-pull-requestsnpx skills add evoelsewhere/evoflux --skill review-pull-requestsgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/review-pull-requests)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/review-pull-requests"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/review-pull-requests.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 | $0.00081 | $0.01186 |
| Opus 5 | $0.00041 | $0.00593 |
| Sonnet 5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
review-pull-requests 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a pull request or merge request
Treat normalized remote review state as authoritative for commits, changes, comments, inline positions, approvals, checks, conflicts, capabilities, and supported actions. Do not load bundled references when this skill activates.
Non-negotiable boundaries
- Use EvoFlux
*_code_review*tools; do not use provider CLIs or raw HTTP. - Use saved credentials; never request, print, or pass tokens.
- Never invent repository selectors, IDs, SHAs, paths, lines, reviewers, capabilities, or merge methods.
- “Review this PR” is read-only inspection unless the user explicitly requests a remote comment, decision, metadata change, merge, close, or reopen.
- Refresh before every position-sensitive or state-changing action and after every mutation. Never act on stale commit or capability state.
State machine
1. RESOLVE
Resolve the exact repository and PR/MR. A workspace scopes one repository; a project may contain several. List current reviews when the number is ambiguous or when the user asks across the project. Do not assume review numbers are globally unique.
Load only list_code_reviews and get_code_review initially. Do not preload
mutation tools. Call get_code_review and record the current source/head commit
plus live capabilities.
2. SELECT MODE
Choose the least-mutating mode that satisfies the request:
- Inspect: analyze and report only.
- Comment: publish only requested feedback.
- Decision: submit approve, request-changes, or comment after fresh gates.
- Lifecycle: update metadata, merge, close, or reopen only when explicit.
Read references/review-playbook.md only for a non-trivial review, re-review, or merge-readiness decision. Do not load it for a one-field status lookup.
3. REVIEW
Establish the intended contract and build a risk map from changed entry points, public interfaces, data, migrations, permissions, concurrency, deployment, and cross-repository effects. Review high-risk surfaces first and validate each finding with a concrete trigger and impact.
What ships with it
6 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.
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 First seen · 122 lines · 81 tokens per session scan A 1955b93b2362
review-pull-requests is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,186 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mobile-developer
Expert knowledge in mobile app development for iOS, Android, and cross-platform solutions.
review
Review a change for correctness, security, and missing tests.
skill-creator
Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update an existing skill) that extends AnkaLoop's capabilities with specialized knowledge, workflows, or tool integrations.
ai-engineer
Expert knowledge in AI/ML development, model deployment, and MLOps practices.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志，提供结构化的故障诊断和报告.
security-best-practices
Security best practices and vulnerability prevention guidelines.