Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rlaope/nennpx agentmods add skills/rlaope/nen/hatsuWrote 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/rlaope/nen/hatsu)<a href="https://agentmods.dev/skills/rlaope/nen/hatsu"><img src="https://agentmods.dev/badge/skills/rlaope/nen/hatsu.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 | $0.00121 | $0.02242 |
| Opus 5 | $0.00060 | $0.01121 |
| Sonnet 5 | $0.00024 | $0.00448 |
| Haiku 4.5 | $0.00012 | $0.00224 |
Grade A, and why
hatsu 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stance
発 Hatsu is the ability you forge for yourself, and the law it runs on is the vow: an ability draws its power from what it refuses to do. A skill is that artifact in engineering clothes — a team's recurring, hard-won practice distilled into a document an agent can load and execute cold. Its precision comes from its restrictions. A skill scoped to everything fires on nothing in particular: the trigger matches half of all requests, the guidance dissolves into generality, and readers learn to route around it. The explicit statement of what a skill will not cover is what makes it fire exactly when it should and hit hard when it does.
The stakes are attrition. Without forged skills, the same lesson is re-taught forever in review comments — the same senior typing the same paragraph on the same class of PR, quarter after quarter. Agents repeat the same failure with fresh confidence in every session, because nothing they load carries the scar tissue. And the discipline itself lives in one practitioner's head, which means it resigns when they do. The prose is not the ability. The restriction is.
Boundaries
If the need is to plan, dispatch, or orchestrate work using skills that already exist, stop — that is manipulator's job. Hatsu fires only when the routing table comes up empty: a recurring need that no existing skill covers. Forging is what you do when there is nothing left to dispatch.
Never forge what already exists. If the recurring pain is unmeasured performance work, that is enhancer; code hostile to change, transmuter; an unchosen goal that needs framing, emitter; an external system's undocumented behavior, specialist; what the system does when a call fails, conjurer. A new skill that paraphrases a sibling splits one trigger surface across two documents, and afterwards neither fires reliably. Check the table before you light the forge.
Revising an existing skill's text is editing, not forging. Sharpen a description, correct a trace, tighten a method step — do it directly against the contract, with the lint as reviewer. The forge is only for abilities that do not exist yet.
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.
- 8d ago First seen · 92 lines · 121 tokens per session scan A d4e0c52f8217
hatsu is a skill published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,242 once invoked, about $0.0006 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…