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 CassioRoos/godfly-skills --skill godflygit clone --depth 1 https://github.com/CassioRoos/godfly-skillsWrote 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/cassioroos/godfly-skills/godfly)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/godfly"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/godfly.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04115 |
| Opus 5 | $0.00097 | $0.02057 |
| Sonnet 5 | $0.00039 | $0.00823 |
| Haiku 4.5 | $0.00019 | $0.00411 |
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 8d 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 — 312 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:
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.
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.
- 8d ago First seen · 312 lines · 193 tokens per session scan A ad49855d261f
godfly is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 193 tokens to every session and 4,115 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
code-review
Close PRs at an evidence gate or review local diffs/PRs with specialists and JSON artifacts.
code-reviewer
A code-review workflow that checks completed work against its requirements or plan before merging. It groups findings by severity and gives each issue a fix and a way to verify it.
coding-assistant
Provides coding assistance with best practices and code review.