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 tighten-for-llmsgit 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/tighten-for-llms)<a href="https://agentmods.dev/skills/noahlz/claude-plugins/tighten-for-llms"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/tighten-for-llms/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/noahlz/claude-plugins/tighten-for-llms"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/tighten-for-llms.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 | $0.00047 | $0.00845 |
| Opus 5 | $0.00023 | $0.00423 |
| Sonnet 5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
tighten-for-llms 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 10d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow steps EXACTLY.
- [ ] 1. Resolve the target
- [ ] 2. Read and classify
- [ ] 3. Tighten
- [ ] 4. Report
1. Resolve the Target
Mode: Dry-run is active when the invocation contains dry-run, or the user's request includes "dry run", "test tightening", or "try tightening". Strip dry-run from the argument before resolving the target file.
Identify the target: an attached file, a pasted block of markdown, or a file path. For binary formats (docx, pdf), extract text first.
If the target is unclear, ask. Typical targets: a recently edited or created skill, agent, reference, rule, README.md, or CLAUDE.md file, or text pasted into the chat session.
2. Read and Classify
Read each file. Record word count.
| Classification | Files |
|---|---|
| LLM-facing | SKILL.md, agent .md, reference .md, rule .md, CLAUDE.md |
| External-facing | README.md |
3. Tighten
Surgical edits per classification. Preserve substance, not structure — collapse or eliminate whole sections when they're mostly padding.
Context check: Read the surrounding sentence before cutting a candidate phrase. Keep phrases that carry meaning — e.g., "You should never commit .env files" (the imperative IS the rule). Cut only padding.
Code block check: If surrounding text makes a block redundant, cut the block and its scaffolding header ("Good example:", "But DO NOT:").
| Edit | LLM-facing | External-facing |
|---|---|---|
| Voice | Imperative — convert "[Subject] should [verb]" → "[Verb]" (e.g., "The assistant should select" → "Select") |
— |
| Remove | Filler ("In order to", "Please note that", "You should", "Make sure to"), purpose framing ("is designed to", "is intended to", "is used to"), section intros that only announce what follows, result descriptions (sentences or sections that describe output shape rather than action), meta-commentary, example scaffolding headers when their example is cut, H1s restating the file name or type (e.g. # CLAUDE.md, # Knock-Knock Joke Skill) |
Internal context, author sections, internal notes |
| Collapse | Verbose lists → tables; multi-bullet elaborations → single dense sentence or fragment | Bullets → tables or paragraphs |
| Headers | — | Scannable noun phrases |
| Preserve | Frontmatter, ---, section headers, code blocks containing information absent from surrounding text |
Code examples, links, install instructions |
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.
- 10d ago First seen · 70 lines · 47 tokens per session scan A da0c4f120287
tighten-for-llms is a skill published in the GitHub repository noahlz/claude-plugins (5 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 845 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…