devflow-plan-critic

devflow-plan-critic is a skill for Claude Code, Codex from KlausFreiberufler/devflow-mcp. It costs 0 tokens per session (2,588 once invoked), scanned A, original, MIT.

A review checklist for examining a DevFlow implementation plan before it moves from planning to approval.

In plain words
What is it for?
Checking whether tasks cover every acceptance criterion, whether tasks are small enough to review, and whether the plan meets seven stated quality dimensions.
Why use it?
It helps find missing requirements, unclear tests, and tasks that are too broad or unrelated.

Skill for Claude CodeCodex

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

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-plan-critic
Any agent
npx skills add KlausFreiberufler/devflow-mcp --skill devflow-plan-critic
Clone the repo
git clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcp

Made for: Claude Code, Codex.

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-plan-critic

README.md
[![agentmods](https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-plan-critic.svg)](https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-plan-critic)
Your own site
<a href="https://agentmods.dev/skills/klausfreiberufler/devflow-mcp/devflow-plan-critic"><img src="https://agentmods.dev/badge/skills/klausfreiberufler/devflow-mcp/devflow-plan-critic.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 2,588 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02588
Opus 5 $0.00000 $0.01294
Sonnet 5 $0.00000 $0.00518
Haiku 4.5 $0.00000 $0.00259

Measured 4d ago against content hash 2725adc420a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devflow-plan-critic 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.

packages/skills/skills/devflow-plan-critic/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: devflow-plan-critic

Purpose: Deep self-critique of a plan before transitioning planning → approval. The agent puts on the reviewer-hat and challenges its own work against 7 quality dimensions.

When to use

Invoke this skill before calling flow_update({currentState: 'approval'}). The pre-tool-use hook prints a reminder, but the responsibility is on the agent: a plan submitted without critique is a plan submitted blind.

The 7 Dimensions

For each dimension, the critic answers a focused question and reports findings.

1. AC-Coverage

Does every Acceptance Criterion have at least one task that addresses it? Do tasks cover all ACs (no orphan tasks, no orphan ACs)?

Common failures:

  • AC mentions a behavior but no task implements it ("user can edit X" → no UI task)
  • Task exists for a sub-behavior not explicitly captured in any AC
  • Acceptance Criterion is too vague to test ("should work well")

2. Task-Granularity

Is each task atomic and fits in less than a day's effort? Can each task be reviewed independently?

Common failures:

  • "Implement feature X" — too coarse, should split into 3-5 tasks
  • "Write tests" — too vague, should split into unit + integration + e2e
  • One task touches >5 files in unrelated areas — likely needs splitting

3. Edge Cases

What happens at the boundaries? Empty input, concurrency, permissions, pre-existing state?

Common failures:

  • No mention of empty/null/zero inputs
  • Race conditions ignored (multi-user, multi-tab)
  • Permission edge unstated ("user can do X" → who specifically? what role?)
  • Migration/upgrade path for existing data missing

4. Wiki-Coverage

Are the relevant ADRs, patterns, and runbooks referenced in the plan? Does the plan drift from existing decisions?

Common failures:

  • Plan introduces a pattern that contradicts an accepted ADR
  • Plan reinvents something already documented as a pattern
  • Plan affects an area that has runbooks, but doesn't reference them
  • Plan extends behavior covered by an existing ADR but doesn't propose an ADR-update

Read the full file on GitHub · 243 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. 4d ago First seen · 243 lines · 0 tokens per session scan A 2725adc420a8

Subscribe to this mod's changes

devflow-plan-critic is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,588 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens