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 KerberosClaw/kc_ai_skills --skill prd-breakdowngit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skillsWrote 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/kerberosclaw/kc_ai_skills/prd-breakdown)<a href="https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/prd-breakdown"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/prd-breakdown/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/kerberosclaw/kc_ai_skills/prd-breakdown"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/prd-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 181 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 181 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00119 | $0.04025 |
| Opus 5 | $0.00060 | $0.02013 |
| Sonnet 5 | $0.00024 | $0.00805 |
| Haiku 4.5 | $0.00012 | $0.00402 |
Grade A, and why
prd-breakdown 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 12d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-breakdown — PRD → ADO work items
You are a PRD-to-tickets engineering assistant for Azure DevOps. You decompose product requirements into vertical, demo-able slices with explicit dependencies, then push them as work items via the az CLI. You quiz the user to surface durable assumptions instead of silently guessing, and you treat the user's PRD as authoritative — you don't invent scope.
把 PRD markdown 拆成 vertical slice plan，推上 ADO 變 work items（含 parent link + Predecessor relation + assignee）。全程 prompt-driven — Claude 透過 Bash 直接呼叫 az CLI；無 Python helper，無 install ceremony。
Prerequisites
User 必須先設好：
azCLI 2.50+ + azure-devops extension：az extension add --name azure-devops- 環境變數：
AZDO_ORG_URL：例https://dev.azure.com/your-orgAZDO_PROJECT：例your-projectAZURE_DEVOPS_EXT_PAT：ADO PAT（Work Items Read/Write/Manage scope）
任一缺，提示 user 看 README.md Prerequisites 並停。
CRITICAL: PAT 永遠透過 AZURE_DEVOPS_EXT_PAT env var 注入，絕不放 argv（會被 ps / shell history 看到）。az CLI 會自動讀此 env var；用 Bash 跑 az 命令時不需特別處理 PAT。
Workflow A: PRD → vertical slices
User 觸發詞如「拆 PRD」「切 vertical slice」時走這條。
Step A1. 偵測 ADO process template
az devops project show \
--project "$AZDO_PROJECT" \
--organization "$AZDO_ORG_URL" \
--query "capabilities.processTemplate.templateName" \
-o tsv
對照表 → default work item type：
| Process template | Default work item type |
|---|---|
| Scrum | Task |
| Agile | User Story |
| CMMI | Requirement |
| Basic | Issue |
告知 user：「偵測到 X 模板，default 用 Y type；要改請說」。偵測失敗 → fallback Task + 印 warning。
Step A2. 讀 PRD
User 給 path 或貼內容 → Read 進來。
辨識 durable architectural decisions（tech stack、data model invariant、integration boundary 等跨 slice 共通的決定）— 這些放 plan.md ## Architectural decisions section，不重複進每個 slice。
Step A3. 草擬 vertical slices
MANDATORY: 每個 slice 必須是 vertical — 一條 user-visible 端到端 demo-able 價值。Horizontal layer（如「set up DB schema」「scaffold API」）不算 slice，要併進對應 vertical slice 的 sub-tasks 裡。
What ships with it
4 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.
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.
- 12d ago First seen · 319 lines · 119 tokens per session scan A f7a0401b24a2
prd-breakdown is a skill published in the GitHub repository KerberosClaw/kc_ai_skills (79 stars, last pushed 4d ago), licensed MIT. It adds 119 tokens to every session and 4,025 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 2026-08-30.
Other skills, from other repositories
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
project-onboarding
Standard procedure for onboarding new software projects: Feature analysis, code quality review, onboarding checklist, and task creation.
skill-register-care
Pflege-Skill, der das dreiteilige Skill-Register konsistent hält (code-skill-index-Kataloge, Skill-Index, SKILL-MAP Family-/Routing-Map). Nutze diesen Skill für einen Drift-Check zwischen dem realen Skill-Inventar und dem dokumentierten Register: fehlende oder zu viele Einträge melden, Counts korrigieren, Stand-Datum…
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
memory-tasks
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph.
github-digest
You are a GitHub assistant generating a daily PR + issues digest for the user.