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 zero-shotgit 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/zero-shot)<a href="https://agentmods.dev/skills/noahlz/claude-plugins/zero-shot"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/zero-shot/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/zero-shot"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/zero-shot.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 | $0.00042 | $0.00772 |
| Opus 5.5 | $0.00017 | $0.00309 |
| Sonnet 5.5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
zero-shot 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 1mo 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.
1. Resolve Mode and Target
- Default to dry-run. Use apply mode only if the user asks to change the file.
- Identify target: attached file, pasted markdown, file path, or skill/agent name.
- If target is missing or ambiguous, ask via
AskUserQuestion.
2. Classify
Read file, record word count, then pick classification:
| Classification | Triggers | Output |
|---|---|---|
| skill | Single-concept SKILL.md or agent without numbered steps |
1–3 imperative sentences (body only) |
| procedural | SKILL.md or agent with numbered checklist or ## N. headers |
Numbered list, 1–3 sentences per step |
| instruction | CLAUDE.md, references/**, rules/**, any non-sequential multi-## doc |
Imperative bullets per ## section |
Precedence:
- Common-knowledge override → skill (jokes, greetings, basic formatting, well-known algorithms).
- Numbered checklist or
## N.headers → procedural. - 2+
##sections, non-sequential → instruction. - Default → skill.
3. Distill
Aggression: trust LLM priors — never restate well-known formats, algorithms, etiquette, or structure the imperative already implies. Delete-test every sentence: if removal doesn't break the task, drop it. Draft, then cut again — first drafts always under-cut.
Reduction targets (min): common-knowledge ≥95%, skill ≥85%, procedural ≥75%, instruction ≥60%. If draft misses, identify under-performing clauses and cut before reporting.
Write in imperative voice. One verb per bullet, no qualifiers.
Cut:
- Framing (
Overview,Background,Introduction), result descriptions, H1s restating the filename. - Examples, rationale, illustrative code, redundant "should not" clauses.
- Format restatement after naming the format.
- Audience qualifiers redundant with
clean/safe. - Error-fallback clauses for common-knowledge tasks — the LLM handles failure.
- Negation pairs where one implies the other.
- Layout instructions implied by a count.
- "Output only X" wrappers when the imperative already scopes the response.
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.
- 1mo ago First seen · 70 lines · 42 tokens per session scan A 2e91661e0dc1
zero-shot is a skill published in the GitHub repository noahlz/claude-plugins (5 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session and 772 once invoked, about $0.0002 per session on Opus 5.5. 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.