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 Flagrare/agent-skills --skill pr-reviewergit clone --depth 1 https://github.com/Flagrare/agent-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/flagrare/agent-skills/pr-reviewer)<a href="https://agentmods.dev/skills/flagrare/agent-skills/pr-reviewer"><img src="https://agentmods.dev/badge/skills/flagrare/agent-skills/pr-reviewer/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/flagrare/agent-skills/pr-reviewer"><img src="https://agentmods.dev/badge/skills/flagrare/agent-skills/pr-reviewer.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 | $0.00082 | $0.06019 |
| Opus 5 | $0.00041 | $0.03010 |
| Sonnet 5 | $0.00016 | $0.01204 |
| Haiku 4.5 | $0.00008 | $0.00602 |
Grade A, and why
pr-reviewer 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 459 lines · 82 tokens per session scan A dda280cbab7a
pr-reviewer is a skill published in the GitHub repository Flagrare/agent-skills (11 stars, last pushed today), with no licence file. It adds 82 tokens to every session and 6,019 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 2026-08-30.
Other skills, from other repositories
pr
A workflow for analyzing branch changes and creating a draft pull request, including a screenshot step when the changes affect the user interface.
transcribe
A spreadsheet-reading workflow for converting XLSX, ODS, or CSV files into Markdown, including documents that use merged cells for layout. It checks that every spreadsheet cell survives the conversion.
use-workflow-tdd-cycle
A test-first coding process based on TDD, or test-driven development: write a failing test, make it pass, then improve the code.
ablate
An ablation workflow for testing a harness by removing one element at a time and measuring whether that element changes the result. A harness is the surrounding setup used to run and evaluate a system.
commit
A workflow that examines staged Git changes, creates a Conventional Commits message, and commits the changes. Conventional Commits use labels such as feat, fix, or docs to describe the kind of change.
preview
A pull-request review command that compares code changes with the plan written in the related GitHub issue or project file.