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 ljucask/pureinn-product-development --skill pm-feature-designgit clone --depth 1 https://github.com/ljucask/pureinn-product-developmentWrote 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/ljucask/pureinn-product-development/pm-feature-design)<a href="https://agentmods.dev/skills/ljucask/pureinn-product-development/pm-feature-design"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-feature-design/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/ljucask/pureinn-product-development/pm-feature-design"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-feature-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.07845 |
| Opus 5 | $0.00049 | $0.03922 |
| Sonnet 5 | $0.00020 | $0.01569 |
| Haiku 4.5 | $0.00010 | $0.00784 |
Grade A, and why
pm-feature-design 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 — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM - Feature Design (JIT)
Agent mode (--agent)
Supports --agent: runs autonomously in a subagent, drafts the artifact from existing inputs, and returns a short summary + coverage note.
- No flag → interactive (default); if inputs are heavy, offer agent mode.
--agent→ obey. First check inputs are complete. Anything missing: do NOT invent it - mark[ASSUMED - what/why]in the output and summary. Never hallucinate to fill a gap.- Review required: the artifact contains commitments - after drafting, require the user's review before finalizing; do not close decisions autonomously.
What this skill does
Produces the Just-In-Time technical design for a single feature immediately before it enters build. This is the FDD Phase 4 (Design by Feature) executed in SDD mode.
JIT vs. upfront design:
| Upfront approach (not used) | This skill (JIT) |
|---|---|
| Feature-Set-level design, written upfront | Feature-level design, written just-in-time |
| Standalone design document | Register updates + sequence diagram embedded in Feature Card |
| Written for an entire Feature Set before the Stripe | Written for one Feature just before build |
What this skill does in one run:
- Reads the Feature Card (Section 1 is stub at this point)
- Discovery Interrogation (Step 1.5) - actively interrogates to surface unknowns and reach precision, calibrated to feature criticality; sorts findings into rules / ACs / subtasks
- Enriches
entities.md- adds exact guard conditions to state transitions relevant to this feature - Enriches
business_rules.mdanddecision_models.md- finalizes rules this feature enforces (Draft → Final); adds brand-new rules surfaced in discovery via the single-rule helpers - Populates Feature Card Section 1 (Biznis Mantinely) - links entities, BR-IDs, TBL-IDs
- Writes Feature Card Section 2 (Acceptance Criteria) - derived from register state + business rules
- Writes Feature Card Subtasks - lightweight nuance helpers captured in discovery
- Generates Mermaid.js sequence diagram + files to modify - writes to Feature Card Section 3
- Pushes description + Sections 1-3 + Subtasks to Notion; sets Feature Card status to
2_Spec_Done(or2b_In_Designif it is a frontend feature whose Figma design still has to be produced - see Step 4d)
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 · 645 lines · 99 tokens per session scan A 912aaaece9db
pm-feature-design is a skill published in the GitHub repository ljucask/pureinn-product-development (2 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 7,845 once invoked, about $0.0005 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
backend-development
A set of instructions for building server-side code such as APIs and database-backed applications. It uses API contracts, data models, the chosen technology stack, and tests as the project’s reference points.
api-contract-first
A set of rules for designing and changing OpenAPI 3.0 interface contracts. These contracts describe how a frontend and backend communicate, including URLs, fields, errors, and status codes.
api-design
Designs interfaces that survive their consumers — resource modeling, errors, versioning, pagination, and compatibility. Use this to design a new API, review one before it ships, decide how to version or deprecate, fix an interface consumers keep misusing, or work out whether a change is breaking.
api-design
API contract design for REST and GraphQL, covering resource shape, URL and header versioning with deprecation windows, RFC 9457 Problem Details error handling, and OpenAPI specs. Use when specifying the wire contract an endpoint exposes, choosing a versioning scheme, or standardizing error response bodies across…
async-jobs
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.
python-backend
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ runtime concerns such as ExceptionGroup, cancellation semantics, and session rollback. Use when building async services, wiring…