fallow: Agent for Claude Code

.agents/agents/ci-integration-reviewer.md

ci-integration-reviewer is an agent for Claude Code from fallow-rs/fallow. It costs 0 tokens per session (986 once invoked), scanned A, original, MIT.

A code-review specialist for CI integrations, which are automated checks that run in a software project’s build pipeline. It focuses on GitHub Actions and GitLab CI templates used to analyze repositories and post results to code reviews.

In plain words
What is it for?
Use it to review CI changes involving scripts, annotations, pull-request or merge-request discussions, authentication tokens, and repeat-run behavior.
Why use it?
It helps catch unsafe shell commands, incorrect JSON filtering, broken review comments, exposed tokens, and duplicate comments when checks run again.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is fallow-rs/fallow's own configuration. It tells Claude Code how to work on fallow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fallow configures →

About the project

Fallow is a command-line static-analysis tool that builds a dependency graph of TypeScript and JavaScript code to identify unused code, duplication, circular dependencies, complexity hotspots, boundary violations, and styling drift. It is for developers reviewing codebases and verifying changes, with catalogue entries that add agent, editor, and workflow integrations.

fallow-rs/fallow · 4,449 stars · on GitHub · docs.fallow.tools

Reuse

Borrowing it

Nothing to install: this file belongs to fallow-rs/fallow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fallow-rs/fallow/main/.agents/agents/ci-integration-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Claude Code.

Wrote 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.

agentmods badge for ci-integration-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fallow-rs/fallow/ci-integration-reviewer.svg)](https://agentmods.dev/agents/fallow-rs/fallow/ci-integration-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fallow-rs/fallow/ci-integration-reviewer"><img src="https://agentmods.dev/badge/agents/fallow-rs/fallow/ci-integration-reviewer.svg" alt="Measured on agentmods" height="20"></a>
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 986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00986
Opus 5 $0.00000 $0.00493
Sonnet 5 $0.00000 $0.00197
Haiku 4.5 $0.00000 $0.00099

Measured 3d ago against content hash d38e7965bad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ci-integration-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 3d 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/ci-integration-reviewer.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review changes to fallow's CI integrations. Decide the provider from the touched paths: action/** is the GitHub composite action used in CI pipelines to analyze repos and post results to PRs, ci/** is the includable GitLab CI template teams add to their .gitlab-ci.yml. The shared checks below apply to both; the provider sections hold only what differs.

What to check

  1. Shell script safety: Quote all variables ("$VAR" not $VAR), use set -euo pipefail, no command injection via user-controlled input
  2. jq filter correctness: Filters must handle empty arrays, null values, missing fields, and grouped output
  3. Comment formatting: Markdown must render correctly on the target platform. Collapsible sections, tables, code blocks
  4. Review comment placement: Inline comments/discussions must target valid diff positions. Out-of-diff issues go in the review body, not as inline comments
  5. Token handling: Document the token requirements. Never log, echo, or embed a token in a URL or error message without masking
  6. Idempotency: Re-running on the same PR/MR should update existing comments, not create duplicates. Use a marker/watermark pattern to find and update prior fallow comments

GitHub specifics

  • action.yml correctness: input types, defaults, required flags, output definitions with clear descriptions and sensible defaults
  • Handle missing inputs gracefully
  • Annotation format: ::error file=...,line=...::message must use correct syntax. Max 10 annotations per step (GitHub limit)
  • Character limits: PR comment body is capped at 65535 characters
  • Action should work with default GITHUB_TOKEN permissions. Document when elevated permissions are needed
  • Binary installation: platform detection, checksum verification, fallback behavior when download fails

GitLab specifics

  • .fallow job definition must be extensible via extends:. Variables must use FALLOW_ prefix consistently. Stage assignment should be configurable
  • Every FALLOW_* variable needs a clear description with a sensible default for the common case
  • Handle a missing GITLAB_TOKEN gracefully (warn, don't fail)
  • GitLab-flavored markdown differs from GitHub: collapsible sections use <details>, code suggestions use suggestion:-0+0 format in discussions
  • Code Quality report must be valid CodeClimate JSON array at the expected gl-code-quality-report.json artifact path
  • Suggestion blocks must use GitLab's specific syntax. Respect FALLOW_MAX_COMMENTS
  • Document PAT requirements (api scope) versus job token limitations
  • Parse cache artifacts should use correct paths and key patterns

Read the full file on GitHub · 77 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. 3d ago First seen · 77 lines · 0 tokens per session scan A d38e7965bad4

Subscribe to this mod's changes

ci-integration-reviewer is an agent published in the GitHub repository fallow-rs/fallow (4,449 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 986 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 2026-09-03.

Related

Other agents, from other repositories

rust-perf-engineer

Reviews diffs touching poly's per-file runner / discovery / cache / engine paths for hot-path regressions — needless allocations/clones, missed borrows, parser-pool misuse, and non-rayon parallelism.

Goldziher/poly · 49 tokens

ring:codebase-explorer

Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).

LerianStudio/ring · 49 tokens

ring:obs-reviewer

Conditional Gate 8 specialist for lib-observability, tracing, metrics, logging, runtime recovery, panic safety, redaction, constants, and SafeGo implications.

LerianStudio/ring · 39 tokens

ring:prompt-reviewer

Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.

LerianStudio/ring · 32 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens