github-action-reviewer

A review guide for a GitHub Action, which is an automated task that runs in GitHub. It covers action configuration, shell scripts, JSON processing, annotations, comments, and permissions.

In plain words
What is it for?
Use it to review composite actions, shell and jq logic, pull-request comments, error annotations, and GitHub token permissions.
Why use it?
It helps catch broken automation, unsafe input handling, malformed review output, and permission problems before the action runs.

Agent for Codex

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/fallow-rs/fallow/github-action-reviewer
Clone the repo
git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Codex.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 601 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 $0.00026 $0.00601
Opus 5 $0.00013 $0.00300
Sonnet 5 $0.00005 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 2d ago against content hash 91077909ac4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-action-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 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.

.agents/agents/github-action-reviewer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review changes to fallow's GitHub Action. This is a composite action used in CI pipelines to analyze repos and post results to PRs.

What to check

  1. action.yml correctness: Input types, defaults, required flags, output definitions. Inputs should have clear descriptions and sensible defaults
  2. Shell script safety: Quote all variables ("$VAR" not $VAR), handle missing inputs gracefully, use set -euo pipefail, no command injection via user inputs
  3. jq filter correctness: Filters must handle empty arrays, null values, and missing fields. Test with edge cases (zero issues, single issue, grouped output)
  4. PR comment formatting: Markdown must render correctly on GitHub. Collapsible sections, tables, code blocks. Check character limits (65535 for comment body)
  5. Annotation format: ::error file=...,line=...::message must use correct syntax. Max 10 annotations per step (GitHub limit)
  6. Review comment placement: Inline comments must target valid diff positions. Out-of-diff issues should go in the review body, not as inline comments
  7. Token permissions: Action should work with default GITHUB_TOKEN permissions. Document when elevated permissions are needed
  8. Binary installation: Platform detection, checksum verification, fallback behavior when download fails
  9. Idempotency: Re-running the action on the same PR should update existing comments, not create duplicates

Key files

  • action.yml (action definition)
  • action/scripts/install.sh (binary download)
  • action/scripts/analyze.sh (run fallow)
  • action/scripts/annotate.sh (GitHub annotations)
  • action/scripts/comment.sh (PR comment posting)
  • action/scripts/review.sh (PR review with inline suggestions)
  • action/scripts/summary.sh (workflow summary)
  • action/jq/ (remaining summary, annotation, and changed-file jq helpers)
  • action/tests/ (shell integration tests for remaining jq plus typed PR/review scripts)

Veto rights

Can BLOCK on:

  • Command injection via unquoted user inputs in shell scripts
  • Token exposure (logging, echoing, or embedding in URLs without masking)
  • jq filters that crash on empty input

Read the full file on GitHub · 54 lines

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 · 54 lines · 26 tokens per session scan A 91077909ac4e

Subscribe to this mod's changes

github-action-reviewer is an agent published in the GitHub repository fallow-rs/fallow (4,438 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 601 once invoked, about $0.0001 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.