devflow-knowledge-completer

devflow-knowledge-completer is a skill for Claude Code from KlausFreiberufler/devflow-mcp. It costs 0 tokens per session (1,129 once invoked), scanned A, original, MIT.

A workflow skill that keeps a project wiki up to date as work progresses. It finds missing topics and requires each one to be added to an existing entry, written as a new entry, or deliberately deferred.

In plain words
What is it for?
Use it during planning and final review to find documentation gaps, update architecture notes or runbooks, and record knowledge that the work uncovered.
Why use it?
It prevents useful decisions and discoveries from being lost after planning or implementation is finished.

Skill for Claude Code

Written for Claude Code: hooks in frontmatter.

Part of the devflow plugin — 24 skills, 8 commands, 2 MCP servers shipped together

Good fit Use it during planning and final review to find documentation gaps, update architecture notes or runbooks, and record knowledge that the work uncovered.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/klausfreiberufler/devflow-mcp/devflow-knowledge-completer
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.

Any agent
npx skills add KlausFreiberufler/devflow-mcp --skill devflow-knowledge-completer
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.

agentmods badge for devflow-knowledge-completer

README.md
[![agentmods](https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-knowledge-completer.svg)](https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-knowledge-completer)
Your own site
<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-knowledge-completer"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-knowledge-completer.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 1,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01129
Opus 5 $0.00000 $0.00564
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 7d ago against content hash b41e88a82a2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

devflow-knowledge-completer 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 7d 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-knowledge-completer/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: devflow-knowledge-completer

LLM-Wiki guarantor. Pattern from Karpathy's LLM-Wiki and OmegaWiki. The wiki is not a side-effect of work — it is the work's compounding artifact. This skill ensures that every flow leaves the wiki at least as complete as it found it.

When to use

  • After devflow-planning and devflow-collision-acknowledged, before submitting plan to approval — so the plan cites the wiki.
  • Again at review → done — so any knowledge unearthed during implementation is captured.

Process

1. Pull the wiki context

GET /api/flows/:id/wiki-context

Returns { relatedAdrs, relatedDocs, parallelFlows, gaps, briefing }. The gaps array is the list of topics that still have no coverage in the wiki.

2. For each gap — decide extend vs create vs intent_defer

For every gap topic, scan relatedAdrs and relatedDocs first. Prefer extend if a related entry exists:

  • extend — a related ADR/pattern/runbook already exists; this flow uncovered something the entry should now mention. Pass entityType + entityId + body (the section to append) and rationale (1–2 sentences why). Backend appends ## Update YYYY-MM-DD — extended by DF-XXX + body to the entry's content. Hook 1 also injects the wikilink into the plan.

  • adr / pattern / runbook — no related entry exists; create a new one via knowledge_check_resolve orchestrator (title + body + rationale). Tag it with the topic AND the broader area (e.g. ["auth", "auth/passkeys"]).

  • intent_defer — the gap is real but genuinely out of scope. Provide horizon and a substantive reason. The intent will resurface in pending_work for a future flow.

Never dismiss. The dismiss resolution-type still exists for backwards compat but is forbidden by this skill — if the gap is irrelevant, it's because the topic-detection misfired, in which case the right move is to extend an existing entry with a one-line "this codebase does not use X" note (so the next flow doesn't trip on the same false positive).

Read the full file on GitHub · 78 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.

  1. 7d ago First seen · 78 lines · 0 tokens per session scan A b41e88a82a2c

Subscribe to this mod's changes

devflow-knowledge-completer is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,129 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.

Related

Other skills, from other repositories

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-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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens