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 KeWang0622/agent-zero-to-hero --skill haiku-mastergit clone --depth 1 https://github.com/KeWang0622/agent-zero-to-heroWrote 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/kewang0622/agent-zero-to-hero/haiku-master)<a href="https://agentmods.dev/skills/kewang0622/agent-zero-to-hero/haiku-master"><img src="https://agentmods.dev/badge/skills/kewang0622/agent-zero-to-hero/haiku-master/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/kewang0622/agent-zero-to-hero/haiku-master"><img src="https://agentmods.dev/badge/skills/kewang0622/agent-zero-to-hero/haiku-master.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 | $0.00022 | $0.00269 |
| Opus 5 | $0.00011 | $0.00134 |
| Sonnet 5 | $0.00004 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
haiku-master 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.
What it actually says
Haiku — the rules
A haiku follows three constraints, in order of importance:
- Three lines. Not four. Not two. Three.
- 5-7-5 syllables. First line: 5. Second line: 7. Third line: 5.
- A seasonal turn (kigo). Reference the natural world. Not a pun.
Style guide
- No rhyming. Rhymes destroy haiku.
- Use ONE concrete image per line. Avoid abstractions.
- The third line should subvert or reframe the first two.
- Lowercase only. No exclamation points.
Example
old pond
a frog jumps in
the sound of water
Procedure
When asked for a haiku:
- Identify the season implied by the prompt (or pick autumn if unclear).
- Choose ONE concrete object as the focus.
- Write the first two lines to set the scene.
- Write the third line to introduce a small surprise or shift.
- Count syllables. Adjust.
- Read it aloud once. If it sounds like prose, rewrite.
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 · 38 lines · 22 tokens per session scan A ed194c13d6d5
haiku-master is a skill published in the GitHub repository KeWang0622/agent-zero-to-hero (49 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 269 once invoked, about $0.0001 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.
Other skills, from other repositories
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.