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 noahlz/claude-plugins --skill de-llmgit clone --depth 1 https://github.com/noahlz/claude-pluginsWrote 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/noahlz/claude-plugins/de-llm)<a href="https://agentmods.dev/skills/noahlz/claude-plugins/de-llm"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/de-llm.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 | $0.00033 | $0.00708 |
| Opus 5 | $0.00016 | $0.00354 |
| Sonnet 5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
de-llm 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Rule: Preserve facts. Strip framing, bloat, and editorial noise.
Checklist
- 1. Read the input
- 2. Pre-scan
- 3. Load pattern details (if step 2 found matches)
- 4. Scan and edit
- 5. Write output
- 6. Report changes
Step 1: Read the Input
Read the input: file path, attached file, or pasted text. Extract text from binary formats (docx, pdf) first.
Step 2: Pre-scan
Without loading references/patterns.md, judge whether any of these patterns are likely present:
| # | Pattern | Action |
|---|---|---|
| 1 | Puffery verbs | Rewrite plainly |
| 2 | Participle bloat | Rewrite or delete |
| 3 | "Not just X, but Y" | Assert Y; drop contrast |
| 4 | Evaluative descriptors | Delete adjective or restructure clause |
| 5 | Self-referential narration | Delete |
| 6 | Vague authority | Delete (unsourced); reattribute (sourced) |
| 7 | Over-hedging on verifiable facts | Strip hedge |
| 8 | Conclusion signposts | Delete signpost; keep conclusion if supported |
| 9 | False-intimacy markers | Delete |
| 10 | Mini-conclusion headers + bullets | Delete header; fold bullets to prose |
| 11 | Bold-as-emphasis | Strip bold; rewrite if claim needs weight |
| 12 | Compressed abstraction; blacklist shape/tension/boundary/unlock/gate/weave/surface/spine/load-bearing/tapestry/interplay/moat/guardrail (zero tolerance) | Expand; blacklist → rewrite or delete |
| 13 | Numeric lead-in to bullets, tables, or section headers | Replace count or drop to noun phrase |
| 14 | Cleft sentences | Rewrite as direct assertion |
- None present → report "No patterns detected." and stop.
- Any present (or uncertain) → continue to step 3.
Step 3: Load Pattern Details
Read references/patterns.md for detection phrases and before/after examples.
Step 4: Scan and Edit
Scan for all 14 patterns. Skip 10 and 11 when input has no inline markdown. Preserve facts; strip framing only.
The pattern 12 blacklist (shape, tension, boundary, unlock, gate, weave, surface, spine, load-bearing, tapestry, interplay, moat, guardrail) is mandatory: always scan for it, and rewrite or delete every metaphorical use — the usual "leave it if unsure" leniency does not apply. Preserve only literal technical uses.
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.
- 6d ago First seen · 71 lines · 33 tokens per session scan A 5c40fb3771d9
de-llm is a skill published in the GitHub repository noahlz/claude-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 708 once invoked, about $0.0002 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 2026-08-31.
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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…