What is devflow-idea-curator?

A periodic backlog-review tool for a project's stored ideas and design records. It groups open intentions, outdated decisions, unlinked pages, contradictions, and frequently changing topics.

Use it during monthly or quarterly project reviews, after milestones, or when the project's documentation checks report problems.

It prevents useful ideas and documentation problems from accumulating unnoticed. Each item is reviewed and either planned, postponed with a time horizon, or rejected with a reason.

devflow-idea-curator — Skill for Claude Code by KlausFreiberufler: A periodic backlog-review tool for a project's stored ideas…

Install

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.

agentmods

npx agentmods add skills/klausfreiberufler/devflow-mcp/devflow-idea-curator

Any agent

npx skills add KlausFreiberufler/devflow-mcp --skill devflow-idea-curator

Clone the repo

git clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcp

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 24 skills, 8 commands, 2 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-idea-curator.svg)](https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-idea-curator)

Your own site

<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-idea-curator"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-idea-curator.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,143 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01143
Opus 5	$0.00000	$0.00571
Sonnet 5	$0.00000	$0.00229
Haiku 4.5	$0.00000	$0.00114

Measured 5d ago against content hash 622e9d9ebe93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

devflow-idea-curator 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 5d 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.

.codex-plugin/skills/devflow-idea-curator/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: devflow-idea-curator

Active idea-pipeline guardian. The wiki is full of organic ideas: deferred intents, stale decisions, orphan patterns, contradictions, hotspots. Without periodic curation they pile up as dead weight. This skill walks the backlog deliberately.

When to use

Once a month for an active project, once a quarter for a slow one.
After a phase / milestone close — to identify what to take on next.
Anytime wiki-lint shows a non-zero LintHealthBar.

Process

1. Pull the backlog

GET /api/projects/:id/ideas

Returns five buckets: openIntents, staleAdrs, orphanPages, contradictions, hotspotTopics. Each item has a prefilledSummary + prefilledDescription ready for Pick & Plan.

2. Walk each bucket — verdict per item

For every item in every bucket, decide one of:

Pick & Plan — promote to a real flow now. Click the button in the UI (or flow_create({ summary: <prefilledSummary>, description: <prefilledDescription> }) directly). The flow inherits the curated text.
Defer — re-affirm as intent, with a fresh horizon (next-quarter, later). For an existing intent, this means updating its frontmatter.horizon. For a stale ADR, re-extend with a "deferred review" note.
Reject — explicit verdict that this idea is no longer needed. Mark the entry's lifecycle_stage as deprecated (for ADRs / patterns) or update intent frontmatter to status: 'rejected'. Always include a 1-line rationale. Iron Law: rejection without rationale is forbidden — the next agent will trip on the same idea.

3. Special cases per bucket

Stale decisions — re-read the ADR. If still factually correct → extend with a dated re-verification note. This bumps updated_at and acknowledges the review. If partially out of date → extend with corrections. If obsolete → supersede with a new ADR.
Orphan pages — entry has zero in/out wiki-links. Either: (a) cross-link from a related entry via extend, or (b) re-classify as intent (document_type='intent', lifecycle_stage='idea'). Never just delete — the entry contains effort that future flows can build on.

Read the full file on GitHub · 83 lines

Changes

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.

5d ago First seen · 83 lines · 0 tokens per session scan A 622e9d9ebe93

Subscribe to this mod's changes

devflow-idea-curator is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,143 tokens. 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.

Project management

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens