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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill idea-to-buildgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/idea-to-build)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/idea-to-build"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/idea-to-build/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/build-with-dhiraj/ai-workflow-framework-portability-kit/idea-to-build"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/idea-to-build.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 | $0.00121 | $0.01550 |
| Opus 5.5 | $0.00048 | $0.00620 |
| Sonnet 5.5 | $0.00024 | $0.00310 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
idea-to-build 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea → Build Pipeline (global, model-tiered)
A cross-surface pipeline that separates ideation, specification, architecture, and implementation by model tier and surface. The durable state between stages is the ticket tracker — never a chat transcript. Any new session (any device) resumes by reading the tracker.
Why tiers: Sonnet is a cheap, fast divergent thinker — ideal brainstorm partner. Fable is the scarce, expensive judgment — spend it ONLY on architecture, planning, review gating, and orchestration. Opus 4.8 agents are strong implementers at a fraction of Fable's cost. Fable never writes the code; it instructs agents who do. Same output quality, fraction of the price.
The four stages
| # | Stage | Surface | Model | State it produces |
|---|---|---|---|---|
| 1 | Brainstorm | Anywhere — claude.ai chat, phone, or Claude Code | Sonnet | A fleshed-out idea (scope, constraints, decisions) |
| 2 | Ticketize | Same surface as 1 (needs tracker MCP) | Sonnet | Tickets with dependencies, blockers, human/agent tags |
| 3 | Plan | MUST be in the project repo (Claude Code) | Fable | Build plan grounded in tickets + actual repo state |
| 4 | Execute | Project repo (Claude Code) | Fable orchestrates; Opus 4.8 agents implement | Shipped, reviewed code; tickets closed |
Hard gate: Stages 3–4 never happen in a plain chat. They require the project file — Fable must see the real repo (what already exists, conventions, migrations half-done) alongside the tickets.
Stage 1 — Brainstorm (Sonnet, anywhere)
- Role: thought partner. Ask probing questions, run WebSearch/research on demand, surface trade-offs, converge on scope. Brain-dump friendly.
- In Claude Code: switch with
/model sonnet, then usesuperpowers:brainstorming(orproduct-management:product-brainstormingfor product/feature ideation, per global precedence). - On claude.ai/phone: plain chat works — no repo needed. Ensure the tracker connector is enabled on claude.ai so Stage 2 can run from the same conversation.
- Done when: the idea's scope, non-goals, and key decisions are settled enough that ticketizing wouldn't invent anything.
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 · 61 lines · 121 tokens per session scan A fe2fc7a1e7f4
idea-to-build is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 16d ago), licensed MIT. It adds 121 tokens to every session and 1,550 once invoked, about $0.0005 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 2026-09-21.
Other skills, from other repositories
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
work-log-claude
A work-log generator that reads Claude Code's local session records and produces an evidence-based Markdown report. It can organise work by project and time period while excluding unrelated session data.
prd-executor
Triggers when: user says "start executing PRD", "start development", "execute breakdown", "implement REQ", or a Dev Agent is assigned to a breakdown directory under docs/. Use this skill to guide the execution of a prddecomposer breakdown from start to finish, enforcing hard gates on requirements confirmation, TDD…
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.