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 Insajin/autopus-adk --skill prdgit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/prd)<a href="https://agentmods.dev/skills/insajin/autopus-adk/prd"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/prd/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/insajin/autopus-adk/prd"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.01905 |
| Opus 5.5 | $0.00004 | $0.00762 |
| Sonnet 5.5 | $0.00002 | $0.00381 |
| Haiku 4.5 | $0.00001 | $0.00191 |
Grade A, and why
prd 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Skill
Skill for creating Product Requirements Documents (PRD) that provide top-level context for the Planning → SPEC pipeline.
PRD Writing Process
Step 1: Request Analysis
Identify the four core dimensions from the user's request:
- What: What product or feature are we building?
- Why: What problem does it solve? What is the business motivation?
- Who: Who are the primary users or stakeholders?
- When: What is the target release or deadline?
Clarify any missing dimensions before proceeding.
Step 1.5: Discovery Q&A
PRD 작성 전에 6개 핵심 질문으로 컨텍스트를 수집합니다. auto idea의 Clarification Ledger 또는 auto plan의 inline intent ledger가 이미 답한 항목은 재질문하지 않고 PRD evidence로 재사용합니다. 사용자 입력이 불충분하면 현재 플랫폼의 question transport로 highest expected-gain 미해결 항목 1개만 확인합니다:
- Problem: 해결하려는 핵심 문제는 무엇인가? (증상이 아닌 근본 원인)
- Target Users: 누가 이것을 사용하는가? (역할, 빈도, 기대)
- Success Metrics: 성공을 어떻게 측정하는가? (정량적 지표 1개 이상)
- Constraints: 기술적/비즈니스적 제약은? (기한, 호환성, 예산)
- Prior Art: 이전에 시도된 접근이나 관련 기능이 있는가?
- Scope Boundary: 이번에 명확히 제외할 것은? (스코프 크리프 방지)
Outcome Lock이나 Must acceptance를 막는 질문만 진행을 차단합니다. 그 밖의 불확실한 항목은 assumed 또는 deferred로 표시하고 PRD의 Open Questions 섹션에 기록합니다. --auto에서는 질문 없이 가장 보수적인 가정을 남기고 Step 2로 진행합니다.
Step 2: Codebase Context Collection
Gather relevant context to ground the PRD in the current state of the system:
- Related files: Identify existing modules, packages, or services affected
- Existing patterns: Review coding conventions, API patterns, data models
- Prior SPECs: Check for related SPEC documents across top-level and submodules
ls .autopus/specs/ */.autopus/specs/ 2>/dev/null # list existing SPECs (top-level + submodules)
cat .autopus/specs/SPEC-*/prd.md */.autopus/specs/SPEC-*/prd.md 2>/dev/null # review related PRDs
Use this context to ensure the PRD aligns with existing architecture and avoids conflicts.
Step 3: PRD Section Authoring
Choose the appropriate mode based on scope:
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 · 193 lines · 11 tokens per session scan A ed939a04c03f
prd is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,905 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
pm
Use when the user wants product requirements rather than code: 'write a PRD', 'product requirements', 'spec this feature for the team', 'ooo pm'. Runs a PM-focused interview with automatic question classification and produces a PRD/PM document. Not for implementation requests.
publish
Publish Seed specification as GitHub Issues for team-based project management.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
project-access
Map, suggest and request the folder access a project needs: map (read-only report), suggest (draft .pi/access.json from this project's grants), provision (submit it for line-by-line operator approval). Use on "what folders can this project reach", "set up folder access", "write .pi/access.json", repeated folder access…