What do I need to use Blast Radius Drill?

The agent's capabilities and environment; The autonomy scope; What's reachable; The reversibility landscape.

Is Blast Radius Drill free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Blast Radius Drill

Q: How do I know the Blast Radius Drill output is good?

The skill verifies itself against its own quality checks: The worst case was walked assuming total compromise, made concrete per capability; Every high-blast capability has a cap that halts; Irreversible actions are denied or gated for autonomous runs; An isolation boundary contains the spread.

🔵 Stable🕐 updated 2026-07-21 🔷 SkillSpec L3 pm-seatbelt

Run the worst-case drill before an agent goes autonomous — the 'if this agent were fully hijacked right now, what's the damage' walk-through, the containment controls (caps, kill-switch, reversibility, isolation), and the recovery plan. Use when asked what's the worst my agent could do, run a blast-radius assessment, prepare for an agent going rogue, or am I ready to let this run unattended. Produces the worst-case walk-through, the containment controls, the reversibility audit, and the incident-recovery runbook.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The agent's capabilities and environment — from the [tool-permission-review](../tool-permission-review/SKILL.md) inventory; the drill runs the worst case through each grant

▸The autonomy scope — how long it runs unattended, how many actions between human checks (longer + more = larger blast radius to contain)

▸What's reachable — the accounts, systems, data, and money the agent's permissions can touch; the worst case is bounded by reach

▸The reversibility landscape — what's backed up, version-controlled, or restorable vs. what's gone-once-done (sent email, spent money, deleted-without-backup, public posts)

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The worst case was walked assuming total compromise, made concrete per capability

✓Every high-blast capability has a cap that halts

✓Irreversible actions are denied or gated for autonomous runs

✓An isolation boundary contains the spread

✓The kill-switch, audit trail, and restore steps exist before go-live

⚠️ What it refuses to do

Do not skip the drill because "it'll probably be fine" — the worst case is found during the incident by those who don't run it

Do not run uncapped autonomy — unbounded actions is unbounded blast radius, hijack or bug alike

Do not let irreversible actions flow unattended — undoable can flow; sent/spent/deleted-forever gates or denies

Do not skip isolation — the boundary is the difference between a bad sandbox and a production breach

Do not improvise recovery — the kill-switch composed mid-runaway is a panic; write it while calm

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="blast-radius-drill"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Blast Radius Drill is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog