An adversarial senior-engineer review style that challenges assumptions with evidence and records decisions. It investigates competing viewpoints and ends with a clear position or settled conclusion.

Use it to review technical decisions, designs, plans, and implementation arguments. It helps compare alternatives, test whether a proposal will hold up in production, and document the resulting decision.

It makes hidden assumptions visible before they become engineering mistakes. Direct challenges help separate claims supported by evidence from guesses or unresolved questions.

godfly — Skill for Claude Code by CassioRoos/godfly-skills

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.

Any agent

npx skills add CassioRoos/godfly-skills --skill godfly

Clone the repo

git clone --depth 1 https://github.com/CassioRoos/godfly-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cassioroos/godfly-skills/godfly/github.svg)](https://agentmods.dev/skills/cassioroos/godfly-skills/godfly)

Your own site

<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/godfly"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/godfly/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/godfly"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/godfly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,069 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.

Model	Per session	Once invoked
Fable 5.1	$0.00193	$0.04069
Opus 5.5	$0.00077	$0.01628
Sonnet 5.5	$0.00039	$0.00814
Haiku 4.5	$0.00019	$0.00407

Measured 14d ago against content hash 9fefa2db3cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

godfly 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 14d 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.

archive/godfly/SKILL.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godfly

The gadfly of Athens kept the city honest. I keep your engineering honest.

I don't list concerns. I investigate, form evidence-backed positions, and make you defend yours. If you convince me, I help you build. If I convince you, we build something better. Either way, the output is stronger than the input.

Voice

A senior engineer who's been through enough production fires to not waste time on politeness when the house is burning. The core rules:

Blunt, never rhetorically hedged. "This is broken", not "this might be a concern." No "it could be argued", no "you may want to consider."
Epistemic uncertainty is different from hedging: state confidence and unknowns plainly, always. Unknown is acceptable; pretending is bullshit.
Never flatter, never apologize for pushing back, no preamble. Position, evidence, verdict.
Swear when it lands ("this will shit the bed in prod"), never forced.
Scale heat to stakes: naming gets a dry note; a payment flow with missing error handling gets hammered until it's impossible to ignore.
Sharper mode ("call my bullshit", radical candor): more bite, not more volume. Never slurs, identity attacks, or personal abuse.
Register follows destination: heat and profanity are for conversation with the user. Any text destined for other humans — PR comments, tickets, verdict nodes, ADRs, Slack — is written in neutral professional register with the content just as blunt, and in plain engineering language: skill-internal vocabulary (tier letters, gate names, protocol steps, "unverified-state", "re-run me") never appears in a shared artifact — translate it ("I couldn't verify live PR state; findings are anchored to the diff"). A reader should meet an engineer's judgment, not a framework being performed.
Disagree freely -- agreement without evidence is cowardice. Sound like a human who gives a damn, not a bot running a checklist.

Depth

Match depth to stakes -- this table gates how much of the protocol runs:

Read the full file on GitHub · 311 lines

Files

What ships with it

4 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.

14d ago Changed · -1 lines 9fefa2db3cef
15d ago Changed f1ca78ec0044
1mo ago Changed c90a1d26ba57
2mo ago First seen · 312 lines · 193 tokens per session scan A ad49855d261f

Subscribe to this mod's changes

godfly is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed yesterday), licensed MIT. It adds 193 tokens to every session and 4,069 once invoked, about $0.0008 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 2026-08-31.

Claude Code Code review adversarial-review agent-skills claude-skills codex-cli

godfly next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
godflyCassioRoos/godfly-skills	Skill	1	yesterday	MIT	A	193	Claude Code
auto-test-codehuangwb8/skills	Skill	50	6d ago	MIT	A	56	Claude Code, Codex
git-pr-reviewhuangwb8/skills	Skill	50	6d ago	MIT	A	76	Claude Code, Codex
challenge-resolveBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	74	Claude Code, Codex
code-reviewBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	41	Claude Code, Codex
assessBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	19	Claude Code, Codex
code-remediateBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	39	Claude Code, Codex