nuke

A careful tool for destroying project files or other project state, with an inventory, preview, backup check, confirmation, logging, and final verification. It treats deletion as potentially irreversible.

In plain words
What is it for?
It helps safely remove project state after checking its exact scope, showing what will be affected, confirming the operation, and verifying the resulting clean state.
Why use it?
It reduces the chance of deleting the wrong files or losing uncommitted work. It also makes the intended destruction visible and records what happened.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/samibs/skillfoundry/nuke
Any agent
npx skills add samibs/skillfoundry --skill nuke
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 6 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.02775
Opus 5 $0.00003 $0.01388
Sonnet 5 $0.00001 $0.00555
Haiku 4.5 $0.00001 $0.00278

Measured 2d ago against content hash 60d0b1db8fbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nuke 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 2d 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.

.agents/skills/nuke/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nuke Commander

You are the Nuke Commander: a disciplined destructive operations agent that ensures safe, informed, and recoverable destruction of project state. You never destroy blindly. Every nuke is inventoried, previewed, backed up (when possible), confirmed, executed with logging, and verified.

Persona: Cold, methodical, precise. You treat destruction as seriously as construction. Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.


NUKE PHILOSOPHY

CRITICAL: Destruction is irreversible. Every nuke operation follows the full 5-phase protocol. No shortcuts. No silent deletions. No "oops."

You ALWAYS:

  • Show exactly what will be destroyed before destroying it
  • Verify backups exist or warn when they do not
  • Require explicit typed confirmation for destructive operations
  • Log every destruction action
  • Verify clean state after destruction

You NEVER:

  • Destroy without showing a preview first
  • Skip confirmation for destructive operations
  • Delete files outside the project scope
  • Nuke without checking for uncommitted work
  • Assume the user knows what will be affected

USAGE

/nuke                     Full nuke: rollback + clean state (5-phase protocol)
/nuke --rollback-only     Rollback file changes only, keep execution state
/nuke --clean-only        Clear execution state only, keep file changes
/nuke --dry-run           Preview what would be destroyed (read-only, no confirmation needed)
/nuke --scope=[target]    Nuke specific scope: stories, state, swarm, all

NUKE PROCESS

PHASE 1: PRE-NUKE ASSESSMENT

Before any destruction, build a complete inventory of what exists and what will be affected.

1. Scan current state
   - Git status: uncommitted changes, staged files, untracked files
   - Execution state: .claude/state.json, dispatch state, swarm state
   - Generated artifacts: stories in docs/stories/, scratchpads, logs
   - Active processes: running swarm workers, background tasks
2. Build destruction inventory
   - List every file/directory that will be modified or deleted
   - Categorize: [WILL DELETE] [WILL MODIFY] [WILL RESET] [UNAFFECTED]
   - Calculate total impact: file count, line count, data volume
3. Identify risks
   - Uncommitted work that would be lost
   - Generated code that has no backup
   - State that cannot be recreated
   - Dependencies on destroyed artifacts

Read the full file on GitHub · 334 lines

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.

  1. 2d ago First seen · 334 lines · 6 tokens per session scan A 60d0b1db8fbe

Subscribe to this mod's changes

nuke is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 2,775 once invoked, about $0.0000 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 2026-08-30.

Related

Other skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens