gemini

A guide for running the pr-reviewer code-review process from the Gemini CLI, a command-line coding assistant, when its coding-skills extension is installed.

In plain words
What is it for?
Use it to review GitHub or GitLab pull requests, clone the repository, run several review rounds, and automate them with a shell loop or scheduled cron job.
Why use it?
It explains how to fetch pull-request data and repeat reviews even though Gemini CLI has no built-in repeating command.

Agent

Install

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.

agentmods
npx agentmods add agents/mdelapenya/coding-skills/gemini
Clone the repo
git clone --depth 1 https://github.com/mdelapenya/coding-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00461
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 2d ago against content hash 5ee3cf415f1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini 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.

skills/pr-reviewer/references/agents/gemini.md · 40 lines

What it actually says

Gemini CLI

Topic file for running pr-reviewer from inside the Gemini CLI (with the coding-skills extension installed).

Fetch tooling

The skill drives its own fetch. Gemini CLI has shell access and is competent with gh (GitHub) and glab (GitLab).

Looping primitive

As of writing, Gemini CLI does not have a /loop primitive — it is an open feature request (gemini-cli#22653; recurring-task scheduling is requested separately at gemini-cli#25415). The official recommendation today is to run Gemini CLI from an external cron for recurring use cases.

Until a real loop primitive ships, use one of:

  • Repeat instruction in the prompt — "Run /pr-reviewer [<num>] up to 3 times, stopping when findings.md records converged: true." Gemini will sequence the rounds itself.
  • External shell driver
    for i in 1 2 3; do
      gemini -p "/pr-reviewer [<num>]"
      grep -q '^- converged: true$' "<base-dir>/findings.md" && break
    done
    
    Most predictable option for CI or scripted reviews.
  • External cron — for periodic re-reviews, schedule the shell driver above with cron. Coarser than per-iteration looping but works today.

--rounds=N is the universal hard stop.

Posting the final report

gh pr review <pr-number> --comment --body-file <path-the-skill-printed>

Always confirm with the user before posting.

References

Changes

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.

  1. 2d ago First seen · 40 lines · 0 tokens per session scan A 5ee3cf415f1c

Subscribe to this mod's changes

gemini is an agent published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 461 tokens. 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.