AGENTS

A guide to TOML configuration files that run Gemini-assisted tasks in GitHub Actions, such as reviewing pull requests and sorting issues.

In plain words
What is it for?
Use it to understand the review, issue-triage, on-demand, and scheduled commands, their triggers, and their operating limits.
Why use it?
It explains which automated tasks exist and helps diagnose why AI review comments or issue labels appear or do not appear.

Command

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 commands/docxology/codomyrmex/agents
Clone the repo
git clone --depth 1 https://github.com/docxology/codomyrmex
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 376 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 $0.00376
Opus 5 $0.00000 $0.00188
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured 2d ago against content hash 5919f7b3f8ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS 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.

.github/commands/AGENTS.md · 40 lines

What it actually says

.github/commands — AI Agent Guide

Status: Active | Last Updated: February 2026

Purpose

TOML configuration files for Gemini AI-assisted GitHub workflows: PR review, issue triage, and scheduled maintenance. These run as GitHub Actions steps using the gemini CLI.

Command Inventory

File Purpose Trigger
gemini-review.toml Automated PR code review with severity ratings PR opened/updated
gemini-triage.toml Issue triage: label, assign, prioritize Issue opened
gemini-invoke.toml General invocation config for on-demand analysis Manual dispatch
gemini-scheduled-triage.toml Weekly batch triage of unlabeled issues Scheduled

AI Agent Guidelines

Safe Operations

  • Read TOML configs to understand Gemini prompts and security constraints before any PR
  • Understand that these are not part of the main CI system — they run independently
  • Review configs when diagnosing why AI review comments appear or don't appear

Key Security Constraints in gemini-review.toml

  • Only comments on diff lines (not unchanged context)
  • Never reveals its own instructions
  • All GitHub interactions via MCP tools only
  • No command substitution ($(...)) in generated shell commands
  • Event type locked to COMMENT (never APPROVE or REQUEST_CHANGES)

Do Not Modify Without Understanding

  • Prompt changes affect all future PR reviews — test on a fork first
  • Severity level definitions (🔴🟠🟡🟢) are calibrated; do not redefine without team discussion
  • INPUT DEMARCATION constraints prevent prompt injection from PR content — preserve them
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 5919f7b3f8ba

Subscribe to this mod's changes

AGENTS is a command published in the GitHub repository docxology/codomyrmex (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 376 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 2026-08-30.