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 agentmods add skills/young1the/pets-driven/hatchnpx skills add young1the/pets-driven --skill hatchgit clone --depth 1 https://github.com/young1the/pets-drivenWhat 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 | $0.00030 | $0.00486 |
| Opus 5 | $0.00015 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
hatch 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 2d 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
Hatch pets-driven
This Codex skill shares the Claude command workflow in
../../commands/hatch.md. Read that command file first, then follow the same
guided workflow one prompt at a time.
Every pets-driven operation goes through the pdd CLI (on the user's PATH). It
reads and writes the shared state file directly and safely — a cross-process
lock keeps it from racing the desktop app — so it works whether or not the app
is running. Never hand-edit the state file or the pet asset folders yourself; go
through pdd. If pdd is not installed, say so and stop.
The command shapes are:
pdd list # existing pets + their cwd
pdd presets # personality ids hatch accepts
pdd hatch # name from the folder, random asset + personality
pdd hatch "<name>" # random asset + personality, current folder
pdd hatch "<name>" --asset <id> --personality <id> --cwd "<folder>"
pdd bind "<petId>" # bind a pet to this folder (--cwd for another)
pdd unbind "<petId>" # release it (cwd -> null)
pdd update --name "<name>" # edit this folder's pet in place
pdd update "<petId>" --asset <id> --personality <id> --note "<text>" --scale <0.5-2>
pdd note # print this folder's pet's note
pdd note "<text>" # write it (--clear erases, - reads stdin)
Nothing is required to hatch: the name defaults to the bound folder's own name,
the asset (look) and personality to a random pick, and the folder to the current
directory. Pass a name, --asset, --personality, or --cwd to choose any of
them.
A pet's cwd may be null — that pet exists with no folder bound and receives
no agent events. Offer to bind such a pet rather than hatching a new one when
the user just wants a pet on this folder.
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.
- 2d ago First seen · 42 lines · 30 tokens per session scan A 5d44d7a67b6d
hatch is a skill published in the GitHub repository young1the/pets-driven (1 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 486 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
front-tech-map
全自动生成前沿技术领域的全景图谱。适用于以技术为核心的赛道（如量子计算、核聚变、AI Agent 等），通过双向挖掘（正向追踪学术源头 + 逆向溯源独角兽创始团队）构建学术→开源→商业化的完整脉络。触发词：「技术mapping」「技术全景图」「technology map」「赛道图谱」「前沿技术」「技术路线图」。.
comparable-company-analysis
生成上市公司可比公司分析报告。当用户请求分析某家公司的竞争对手、可比公司、同业对比、竞品分析、对标公司分析时使用此技能。.
财经分析工具包
专业的财经分析工具包，提供股票分析、市场趋势预测、投资建议等功能，帮助Agent进行财经决策和市场研究。.
local-research
Search local notes and distinguish evidence from unsupported claims.
fable-mode
A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check, real-product…
codebase-discovery
Extract domain, architecture, business rules, workflows and a business glossary from an existing (often poorly documented) codebase, then validate the findings with a senior BA/Product Owner one question at a time. Produces onboarding-grade docs under docs/ that give a new team member — human or AI — enough context to…