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 Dragoon0x/dragoon-skills --skill carefulgit clone --depth 1 https://github.com/Dragoon0x/dragoon-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/dragoon0x/dragoon-skills/careful)<a href="https://agentmods.dev/skills/dragoon0x/dragoon-skills/careful"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/careful/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/dragoon0x/dragoon-skills/careful"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/careful.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00103 | $0.00260 |
| Opus 5.5 | $0.00041 | $0.00104 |
| Sonnet 5.5 | $0.00021 | $0.00052 |
| Haiku 4.5 | $0.00010 | $0.00026 |
Grade C, and why
careful scanned grade C 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 1mo 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 deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
description: Write a checklist of destructive commands the user wants to think twice about (rm -rf, force push, hard reset, db drop, etc.) to .dragoon/CAREFUL.md. dragoon does NOT block commands at runtime - this is a di What it actually says
/careful
Discipline-tool checklist for destructive commands.
When to use
- Setting up a new project or onboarding an agent
- After a destructive accident, codify the rule
- The user says "set up guardrails", "what should the agent not do"
What it writes
.dragoon/CAREFUL.md with two sections:
- destructive commands to confirm before running (rm -rf, force push, etc.)
- destructive commands the agent should NEVER run without explicit user prompt
This is not a runtime block. It's a read-before-act discipline aid.
Run it
dragoon careful --apply
dragoon careful --show
What ships with it
1 file 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.
- 1mo ago First seen · 31 lines · 103 tokens per session scan C 8a78ac447223
careful is a skill published in the GitHub repository Dragoon0x/dragoon-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 103 tokens to every session and 260 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C 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
ship
Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
kb-github-shared-instructions
Reference data, not a reviewer. Persona, authentication, output and reporting rules every GitHub skill follows.
kb-github-workflow-standards
Reference data, not a reviewer. Core standards for GitHub workflow agents: authentication, repository discovery, dual MD+HTML output, accessibility compliance, safety rules, and parallel execution patterns.
kb-github-a11y-scanner
Reference data, not a reviewer. Integrate GitHub Accessibility Scanner. Detects configuration, parses scanner issues, correlates with local scans, and tracks Copilot-assigned fixes.
kb-github-analytics-scoring
Reference data, not a reviewer. Score repository health (0-100, A-F grades), priorities, and delta tracking. Includes velocity metrics, confidence levels, and bottleneck detection.
kb-github-scanning
Reference data, not a reviewer. Search GitHub for issues, PRs, discussions, releases, and alerts. Includes query construction, date range handling, repo scoping, and cross-repo intelligence.