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.
npx skills add dcramer/agents --skill garfieldgit clone --depth 1 https://github.com/dcramer/agentsWrote 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.
[](https://agentmods.dev/skills/dcramer/agents/garfield)<a href="https://agentmods.dev/skills/dcramer/agents/garfield"><img src="https://agentmods.dev/badge/skills/dcramer/agents/garfield/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dcramer/agents/garfield"><img src="https://agentmods.dev/badge/skills/dcramer/agents/garfield.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 49 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01742 |
| Opus 5.5 | $0.00024 | $0.00697 |
| Sonnet 5.5 | $0.00012 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
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 2mo 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.
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 anyREADME.mdorpolicy-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.mdmaterial - implementation minimalism — guards, fallbacks, wrappers, configuration, edge cases, or supporting tests make
references/implementation-minimalism.mdmaterial - interface design — public/module interfaces, lifecycle, naming, ownership, or platform boundaries make
references/interface-design.mdmaterial - 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
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.
- agents/openai.yaml 241 B
- evals/.gitattributes 59 B
- evals/cases/bounded-review-delegation.yaml 994 B
- evals/cases/concise-handoff.yaml 886 B
- evals/cases/effective-review-plan.yaml 965 B
- evals/cases/evidence-grounded-triage.yaml 1.0 KB
- evals/cases/independent-verification.yaml 923 B
- evals/cases/intent-preserving-repair.yaml 884 B
- evals/cases/slice-framing.yaml 931 B
- evals/cases/targeted-validation-and-stopping.yaml 976 B
- evals/fixtures/cli-slice/.eval-change.patch 1.8 KB
- evals/fixtures/cli-slice/.gitignore 70 B
- evals/fixtures/cli-slice/notes/local.txt 42 B
- evals/fixtures/cli-slice/package.json 125 B
- evals/fixtures/cli-slice/README.md 126 B
- evals/fixtures/cli-slice/src/report.mjs 198 B runs code
- evals/fixtures/cli-slice/test/report.test.mjs 371 B runs code
- evals/fixtures/generated-risk/.eval-change.patch 842 B
- evals/fixtures/generated-risk/.gitignore 70 B
- evals/fixtures/generated-risk/generated/statuses.mjs 82 B runs code
- evals/fixtures/generated-risk/package.json 189 B
- evals/fixtures/generated-risk/schema/status.json 37 B
- evals/fixtures/generated-risk/scripts/check-generated.mjs 295 B runs code
- evals/fixtures/generated-risk/src/status.mjs 131 B runs code
- evals/fixtures/generated-risk/test/status.test.mjs 311 B runs code
- evals/fixtures/policy-overlap/.eval-change.patch 1.4 KB
- evals/fixtures/policy-overlap/.gitignore 70 B
- evals/fixtures/policy-overlap/package.json 130 B
- evals/fixtures/policy-overlap/policies/policy-template.md 89 B
- evals/fixtures/policy-overlap/policies/testing.md 308 B
- evals/fixtures/policy-overlap/src/cache.mjs 110 B runs code
- evals/fixtures/policy-overlap/test/cache.test.mjs 290 B runs code
- evals/fixtures/review-queue/.eval-change.patch 1.7 KB
- evals/fixtures/review-queue/.gitignore 70 B
- evals/fixtures/review-queue/package.json 128 B
- evals/fixtures/review-queue/README.md 98 B
- evals/fixtures/review-queue/src/adapter.mjs 115 B runs code
- evals/fixtures/review-queue/test/adapter.test.mjs 269 B runs code
- README.md 2.3 KB
- references/code-comments.md 1.2 KB
- references/implementation-minimalism.md 1.9 KB
- references/interface-design.md 3.1 KB
- references/policy-template.md 467 B
- references/review-lanes.md 7.0 KB
- references/test-quality.md 2.9 KB
- SOURCES.md 30 KB
- spec.md 9.3 KB
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.
- 2mo ago First seen · 112 lines · 59 tokens per session scan A d73b66b115c5
garfield is a skill published in the GitHub repository dcramer/agents (57 stars, last pushed 28d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,742 once invoked, about $0.0002 per session on Opus 5.5. 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.
garfield compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| garfielddcramer/agents | Skill | 57 | 28d ago | Apache-2.0 | A | 59 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.6k | today | MIT | A | 17 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.6k | today | MIT | A | 20 | Claude Code |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 7d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 956 | today | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 2d ago | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 162 | Claude Code, Codex |