Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stefaniuk/loadoutnpx agentmods add commands/stefaniuk/loadout/util.gh-pr-reviewWrote 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/commands/stefaniuk/loadout/util.gh-pr-review)<a href="https://agentmods.dev/commands/stefaniuk/loadout/util.gh-pr-review"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/util.gh-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/commands/stefaniuk/loadout/util.gh-pr-review"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/util.gh-pr-review.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 | $0.00008 | $0.05440 |
| Opus 5 | $0.00004 | $0.02720 |
| Sonnet 5 | $0.00002 | $0.01088 |
| Haiku 4.5 | $0.00001 | $0.00544 |
Grade A, and why
util.gh-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 yesterday.
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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandatory preparation:
- Read the constitution and honour its non-negotiable rules.
- Read the Pull Request template at pull_request_template.md only to understand the author's reporting structure; the review output uses its own structure defined below.
- Read the technology-specific instructions only for languages actually touched on this branch (look at the stat in the bounded report; do not preload every instruction file). For example python.instructions.md, shell.instructions.md, makefile.instructions.md.
- Load design context (
.copilot/analysis/repository-map.md,component-*.md,runtime-flow-*.md,domain-*.md,c4-*.dsl,*-infrastructure.*) only if those files actually exist and only when the diff materially touches the components they describe. Do not block the review on missing design context.
Goal 🎯
Act as a senior peer reviewer for the pull request that merges this branch into its detected base branch (see the Scope policy). Produce a focused, constructive, evidence-based review whose primary job is to:
- Verify intent vs implementation - does the code do what the PR title/description and commit messages claim, no more and no less?
- Surface merge-blockers first - correctness, safety, security, contract, and data-integrity issues.
- Coach, don't nitpick - every finding is actionable, prioritised, and evidence-backed; lower-severity items are suggestions, not demands.
The reviewer's deliverable is a Markdown report saved under .copilot/analysis/gh-pr-review-YYYYMMDD-<slug>.report.md (where <slug> is pr-<number> when a PR is known, otherwise the sanitised branch name; this prevents collisions when several PRs are reviewed on the same day) and an overall verdict (Approve / Request changes / Comment).
Quality bar (apply to every finding)
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.
- yesterday First seen · 359 lines · 8 tokens per session scan A 869ec547e976
util.gh-pr-review is a command published in the GitHub repository stefaniuk/loadout (1 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 5,440 once invoked, about $0.0000 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 2026-09-12.
Other commands, from other repositories
sddp-qc
Command description: Run quality control against the implemented feature. Argument hint: [optional: testing focus such as unit tests, security audit, requirements sync] Command category: feature-delivery Prerequisites: spec, plan, tasks, implementation:complete.
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-checklist
Command description: Generate and evaluate a requirements quality checklist. Argument hint: [optional: quality focus or feature context] Command category: feature-delivery Prerequisites: spec, plan.
sddp-plan
Command description: Create an implementation plan from the current feature specification. Argument hint: [optional: planning constraints or focus areas] Command category: feature-delivery Prerequisites: spec.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-specify
Command description: Create a feature specification from a feature description. Argument hint: [feature description] Command category: feature-delivery Prerequisites: project-instructions.