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 safe-opsgit 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/safe-ops)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/safe-ops"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/safe-ops.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 | $0.00134 | $0.00760 |
| Opus 5 | $0.00067 | $0.00380 |
| Sonnet 5 | $0.00027 | $0.00152 |
| Haiku 4.5 | $0.00013 | $0.00076 |
Grade B, and why
safe-ops scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| **L4** | Destructive or irreversible | Dry-run + Explicit Confirm + Rollback plan | `drop table`, `rm -rf`, force push, scale down | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Ops
Execute system operations safely with risk classification, dry-run previews, confirmation gates, and audit trails.
Quick Start
Before ANY system operation:
- Classify risk (L1-L4)
- Dry-run / preview the operation (L2+)
- Confirm with user (L3+)
- Execute and capture output
- Log what was done with rollback info (L2+)
Environment and Precedence Rules
- An environment you cannot classify is production until proven otherwise. Production targets are treated one risk level higher (a production L3 gets L4 ceremony).
- L3+ confirmation must name all of: (1) the exact command/action, (2) the environment and target, (3) whether it is read-only or mutating, and (4) the expected effect and scope. A bare "Proceed? (yes/no)" without those items is not confirmation, and the user's original request does not count as confirmation for L3+.
- When another active skill defines a stricter boundary for the same operation (e.g. a QA or deployment skill with its own environment boundary), the stricter rule wins.
Safety Protocol
Read cookbook/safety-protocol.md - ALWAYS load this first
Operation Domains
Infrastructure (Docker, K8s, Cloud)
Read cookbook/infrastructure.md
Dev Workflow (Git, CI/CD, PRs)
Data & Services (DB, APIs, Caches)
Read cookbook/data-services.md
Local System (Files, Processes, Env)
Risk Levels
| Level | Impact | Requires | Examples |
|---|---|---|---|
| L1 | Read-only, no side effects | Nothing | git status, docker ps, ls |
| L2 | Local, reversible changes | Preview | git commit, file edits, docker build |
| L3 | Remote or hard-to-reverse | Dry-run + Confirm | git push, docker push, deploy, DB write |
| L4 | Destructive or irreversible | Dry-run + Explicit Confirm + Rollback plan | drop table, rm -rf, force push, scale down |
What ships with it
5 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 · 72 lines · 134 tokens per session scan B 231820b10f35
safe-ops is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 134 tokens to every session and 760 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
PR Description Writer
Writes clear, thorough pull request descriptions from a diff or list of changes.
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…