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/klausfreiberufler/devflow-mcp/devflow-area-ideationnpx skills add KlausFreiberufler/devflow-mcp --skill devflow-area-ideationgit clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcpWrote 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/klausfreiberufler/devflow-mcp/devflow-area-ideation)<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-area-ideation"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-area-ideation.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00967 |
| Opus 5 | $0.00033 | $0.00483 |
| Sonnet 5 | $0.00013 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
devflow-area-ideation 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: devflow-area-ideation
Wiki-grounded ideation. When the user clicks "Copy prompt" on the IdeasPage and pastes the result into Claude, this skill drives the response. The prompt has the Wiki-context pre-loaded — don't ignore it, use it.
When to use
- The user pasted a prompt that starts with
# Idea-Hunt: <area> for this project. - The prompt contains a
## Contextsection with ADRs / patterns / runbooks already listed. - Tasks ask for "3 concrete next-step ideas" or "3 market-opportunity ideas".
Process
1. Read the prompt's Context section completely
The IdeasPage already pulled the relevant wiki snapshot. Don't re-fetch the same data — extend it:
wiki_get_briefing({ flowId })— only if you have an active flow context (rare for ideation).wiki_search({ q: <area-name> })— to surface entries the prompt didn't pre-load.wiki_get_index({ projectId })— to see if the area has more entries grouped by lifecycle.pending_work({ projectId, tags: [<area>] })— what's already in flight.
2. For each candidate idea — verify wiki-grounding
For every idea you generate, ask: which existing ADR / pattern / runbook does this build on? If you can't name one, the idea is too thin — discard or refine.
If the area is market (signal: prompt says "market-opportunity ideas"), allow looser grounding — but still name ONE wiki entry per idea ("extends [[ADR-X]]" or "fills the gap left by [[pattern:Y]]").
3. Output exactly 3 ideas as JSON
[
{
"summary": "Concise ticket-style summary (≤80 chars)",
"description": "2-3 sentences: what + why, grounded in wiki",
"wikiEvidence": ["ADR-014", "pattern:rate-limit"],
"kindOfWork": "feature" | "refactor" | "research" | "runbook" | "adr"
}
]
After the JSON, add a 2-line verdict explaining if the area looks healthy (rich context → easy ideation) or thin (worth investing in wiki harvesting first).
4. Optional: emit discipline-token
devflow_token_emit({
flowId: <currentFlowId or null>,
skillName: 'devflow-area-ideation',
evidence: {
area: '<area-name>',
ideas: [{ summary, kindOfWork, wikiEvidence }],
verdict: 'healthy' | 'thin',
completedAt: new Date().toISOString()
}
})
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.
- 4d ago First seen · 86 lines · 66 tokens per session scan A 6582ce16c9ba
devflow-area-ideation is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 967 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…