Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add web-abin/OpenGeno/plugin install opengenoWrote 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/web-abin/opengeno/geno-init)<a href="https://agentmods.dev/skills/web-abin/opengeno/geno-init"><img src="https://agentmods.dev/badge/skills/web-abin/opengeno/geno-init.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 | $0.00134 | $0.03026 |
| Opus 5 | $0.00067 | $0.01513 |
| Sonnet 5 | $0.00027 | $0.00605 |
| Haiku 4.5 | $0.00013 | $0.00303 |
Grade A, and why
geno-init 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 7d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/geno-init
Bootstrap an OpenGeno feature tree for a project. Run once per
project. If feat-tree/ already exists, abort and direct the user to
/geno-sync instead.
This skill is the only command needed to set up the tree — and the only way to introduce the OpenGeno workflow rules into CLAUDE.md / AGENTS.md.
Pre-flight
test -d feat-tree && echo "tree exists, abort" || echo "ok to init"
If the tree exists, stop. Tell the user to use /geno-sync for
drift, or to manually add new feature docs from the templates in this
skill's templates/ directory.
Workflow
Step 1 — Pick the documentation language
Use AskUserQuestion:
- Question: "Which language should OpenGeno write the feature tree in?"
- Options (English first, marked recommended):
- English (Recommended)
- 中文 (Chinese)
Store the choice as LANG = "en" or LANG = "zh". Critical: from
this point on, every file you write under feat-tree/, every section
heading, every prose line, every comment, every example value, every
TODO placeholder MUST be in the chosen language. Do not mix languages
within the tree.
If the user picks Chinese, you must write Chinese exclusively for the rest of this skill's execution. Do not silently fall back to English even for "small" things like field labels — the user will read every doc in their chosen language; mixing is jarring.
Step 2 — Pick the drift mode
Use AskUserQuestion, phrased in the chosen language:
- Options:
- Warn (default): print drift summary at session-end, do not block
- Block: refuse to end session if drift exists
Store as DRIFT_MODE.
Step 3 — Pick the generation mode
Use AskUserQuestion, phrased in the chosen language:
- Options:
- Stub (Recommended): shallow scan, generate L3 stubs, fill on demand
- One-shot full docs: deeper scan, attempt to fill every L3 section now
Store as MODE = "stub" or MODE = "full".
stub is the default because deeper code reading is expensive and
hallucination-prone — the user should opt in deliberately. full is
useful when the codebase is small and stable, and the user wants a
complete first-pass tree to review wholesale rather than incrementally.
What ships with it
15 files 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.
- reference.md 10 KB
- scripts/drift-check.sh 2.8 KB runs code
- scripts/post-edit-warn.sh 1.9 KB runs code
- scripts/stop-check.sh 2.8 KB runs code
- templates/claude-md-injection.md 3.7 KB
- templates/claude-md-injection.zh.md 3.6 KB
- templates/feat-tree.json 93 B
- templates/feature-logic.md 1.2 KB
- templates/feature-logic.zh.md 1.1 KB
- templates/feature-ui.md 2.1 KB
- templates/feature-ui.zh.md 2.0 KB
- templates/module-index.md 1.1 KB
- templates/module-index.zh.md 1011 B
- templates/root-index.md 1.4 KB
- templates/root-index.zh.md 1.3 KB
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.
- 7d ago First seen · 280 lines · 134 tokens per session scan A 73bacc412ebb
geno-init is a skill published in the GitHub repository web-abin/OpenGeno (5 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 3,026 once invoked, about $0.0007 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
mermaiddoc
Skill "mermaiddoc" from stefanrossmeier/ai-craftkit, covering mermaiddoc skill, purpose, supported diagram types, slash command and required output files.
docs
Document hygiene — find stale, obsolete, duplicate, and scattered docs. Sync, consolidate, update, or remove. Interactive.
qa
QA testing — browse like a real user, document bugs, report only. Never fixes.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
security-audit
Java security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java. Use when reviewing code security, before releases, or when user asks about vulnerabilities.