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-code-criticnpx skills add KlausFreiberufler/devflow-mcp --skill devflow-code-criticgit clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcpWhat 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 | $0.00111 | $0.02161 |
| Opus 5 | $0.00056 | $0.01081 |
| Sonnet 5 | $0.00022 | $0.00432 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
devflow-code-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 2d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: devflow-code-critic
Purpose: Deep self-critique of an implementation before transitioning
in_progress → review. The agent puts on the reviewer-hat and challenges its own code against 7 quality dimensions.
When to use
Invoke this skill before calling flow_update({currentState: 'review'}). The pre-tool-use hook prints a reminder, but the responsibility is on the agent: code submitted without critique is code submitted blind.
The 7 Dimensions
For each dimension, the critic answers a focused question and reports findings.
1. AC-Implementation
Was every Acceptance Criterion actually implemented? Not just touched — fully met?
Common failures:
- AC says "X is editable" but only the read-path is implemented
- AC says "validate Y" but only happy-path tested, edge-cases skipped
- AC mentioned in plan but never made it into code (drift)
2. Test-Coverage
Were tests added for every behavior change? Do they actually exercise the AC?
Common failures:
- New function but no test
- Test added but doesn't assert the AC's specific behavior
- Test passes but only because the assertion is too weak (
.toBeTruthy()on anything truthy) - Critical-path code without integration/e2e test
3. Iron-Laws (skill-specific)
Were the relevant DevFlow iron-laws followed?
Check at minimum:
devflow-tdd— failing test before production code? Each cycle has evidence?devflow-pattern-reuse— was an existing pattern reused, or did we invent?devflow-knowledge-completer— extend > create > defer > NEVER dismissdevflow-collision-acknowledged— checked for parallel flows in this area?
4. ADR-Compliance
Are there ADRs that govern this area? Does the code follow them?
Common failures:
- ADR-X says "use Y", code uses Z without justification
- New decision implicit in code that contradicts an existing ADR
- Code introduces a pattern that should be promoted to ADR but wasn't
5. Plan-Reconciliation (DF-310 alignment)
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.
- 2d ago First seen · 230 lines · 0 tokens per session scan A 09fef640e910
devflow-code-critic is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 111 tokens to every session and 2,161 once invoked, about $0.0006 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.
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.
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.
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.
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…