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 agentmods add skills/emasoft/claude-plugins-validation/cpv-devitalize-threatsnpx skills add Emasoft/claude-plugins-validation --skill cpv-devitalize-threatsgit clone --depth 1 https://github.com/Emasoft/claude-plugins-validationWrote 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/emasoft/claude-plugins-validation/cpv-devitalize-threats)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-devitalize-threats"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-devitalize-threats.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 | $0.00157 | $0.03581 |
| Opus 5 | $0.00078 | $0.01791 |
| Sonnet 5 | $0.00031 | $0.00716 |
| Haiku 4.5 | $0.00016 | $0.00358 |
Grade B, and why
cpv-devitalize-threats scanned grade B with 3 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 6d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
enough on its own — the `curl … | bash` token pair is what Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
enough on its own — the `curl … | bash` token pair is what Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
a rule or relaxing --strict. Maps each threat shape (live os.system / How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devitalize Threats — execution-shape to inert-data transformation catalog
Overview
Devitalization rewrites the shape of a flagged construct so the threat
itself disappears — not the finding. A construct stops firing because it
is now provably data that can never reach an execution sink, verified by
the same unchanged scanner at the same --strict level.
The one rule: provably-passive or don't touch it. Never mute a rule,
never add an ignore/skip flag, never weaken --strict, never edit a CPV
validator. The only acceptable "clear" is the scanner no longer firing
because the shape is now inert — not because it was silenced. The bar
is irreversible inertness: an execution-critical piece of the
construct is REMOVED ENTIRELY from the plugin — not encrypted, not
compiled to a binary, not regenerated or emitted programmatically at
runtime, not hidden/concealed/obfuscated. The missing piece is
ABSENT, not hidden. A construct that could be reassembled into a
runnable form at runtime is NOT devitalized.
This is the author-side counterpart to CPV's scanner-side inert-proof discriminators. The scanner already auto-clears a few shapes it can mechanically prove harmless (raw-string regex signatures, defanged doc illustrations, placeholder secrets). Devitalization rewrites the plugin's source so a flagged construct matches one of those shapes, or is removed/nominalized so no rule fires at all.
Prerequisites
- A security report from
validate_security.py+ native skillaudit (the cpv-plugin-devitalizer-agent agent produces it via the isolation launcher). - The flagged file open, with each finding's
file:line+rule_id+ matched span.
The two questions before any transform (decision gate)
- Q1 — Is this code LOAD-BEARING? Does live behavior depend on this construct executing, reachable from any entry point (hooks.json, command/agent dispatch, dynamic import, glob loader, re-export, test)?
- Q2 — Can the flagged construct be expressed as data with NO path to a sink? A detector needle, a doc illustration, a dead example, or a dynamic value constrained to a finite known set.
What ships with it
3 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.
- 6d ago First seen · 262 lines · 157 tokens per session scan B f8eb5ec412eb
cpv-devitalize-threats is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 3,581 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…