garfield

A workflow for coordinating a focused review of a code change, applying intent-preserving fixes, and validating the result. It is named Garfield and is intended for implementation hardening after a meaningful code slice.

In plain words
What is it for?
Use it when explicitly requested to run a review-fix-verify loop on an implementation before handoff.
Why use it?
It catches concrete problems in the current change while keeping the requested behavior and avoiding unrelated work.

Skill for Claude CodeCodex

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 skills/dcramer/agents/garfield
Any agent
npx skills add dcramer/agents --skill garfield
Clone the repo
git clone --depth 1 https://github.com/dcramer/agents

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,742 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 $0.00059 $0.01742
Opus 5 $0.00030 $0.00871
Sonnet 5 $0.00012 $0.00348
Haiku 4.5 $0.00006 $0.00174

Measured 2d ago against content hash d73b66b115c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

garfield 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.

The scan reads SKILL.md. This mod also ships 10 executable files (evals/fixtures/cli-slice/src/report.mjs, evals/fixtures/cli-slice/test/report.test.mjs, evals/fixtures/generated-risk/generated/statuses.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/garfield/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Garfield

Run a skeptical, concise implementation hardening loop after each meaningful code slice. Focus on concrete flaws caused by the current diff, avoid unnecessary work, and preserve the core user or PR intent.

Never activate Garfield unless the user explicitly invokes it. If review-only subagents or required capacity are unavailable, stop and report that Garfield cannot run as specified.

Frame the slice

Before review, inspect:

  • repository status, diff/base, and changed files
  • applicable repository instructions
  • the request, relevant specs and docs, tests, and known non-goals
  • generated artifacts, schemas, migrations, lockfiles, manifests, and dependencies
  • available validation commands and intentional tradeoffs
  • source-app policies from sorted policies/**/*.md, excluding any README.md or policy-template.md

Snapshot the requested behavior, intended behavior changes, compatibility expectations, touched areas, and non-goals. Scope review to the current diff and directly related files. Preserve unrelated dirty-worktree changes.

Build the effective review plan

Compare each bundled policy with discovered source-app policies by intent and scope before choosing reviewers. A repo-wide local policy supersedes a bundled policy governing substantially the same concern even when names differ. A narrower or adjacent local policy supplements it. Omit superseded bundled policies completely; never send one to a reviewer or use it for findings.

Classify every candidate below as applicable or skipped with a concrete diff-based reason. Confidence that the code looks safe is not a skip reason.

  • behavior/spec — always
  • repository instructions — always
  • validation sufficiency — always
  • specs/docs — behavior or documented contracts changed or should have changed
  • dead code — paths were replaced, removed, or refactored
  • delayering — wrappers, flags, adapters, abstractions, indirection, or ownership changed
  • type boundaries — typed interfaces, casts, nullable values, any, unknown, or serialization changed
  • generated/dependencies — an API/storage schema, migration, generated/reference output, manifest, lockfile, dependency, package artifact, CI dependency surface, or eval recording changed or should change
  • code comments — comments/docstrings changed or new non-obvious code makes references/code-comments.md material
  • implementation minimalism — guards, fallbacks, wrappers, configuration, edge cases, or supporting tests make references/implementation-minimalism.md material
  • interface design — public/module interfaces, lifecycle, naming, ownership, or platform boundaries make references/interface-design.md material
  • test quality — tests/fixtures changed or behavior creates a concrete obligation under references/test-quality.md
  • each effective source-app policy — its scope governs the slice

Read the full file on GitHub · 112 lines

Files

What ships with it

47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 112 lines · 59 tokens per session scan A d73b66b115c5

Subscribe to this mod's changes

garfield is a skill published in the GitHub repository dcramer/agents (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,742 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens