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-corenpx skills add KlausFreiberufler/devflow-mcp --skill devflow-coregit 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 | $0.00037 | $0.01419 |
| Opus 5 | $0.00018 | $0.00709 |
| Sonnet 5 | $0.00007 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
devflow-core 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevFlow — Core Workflow
This project uses DevFlow for structured AI development. Every change flows through a state machine enforced by the MCP server.
State Machine
idea → planning → approval → ready → in_progress → review → done
approvalandrevieware wait states — user must act in DevFlow UIreadyanddoneare auto states — transitioned automatically
Start of Every Session
Before any tool call other than flow_list, flow_create, or devflow_status, you MUST call:
devflow_init({ flowId: "..." })
Without an active session, all MCP tools are blocked with a 403.
Use /devflow-start <DF-XXX> as a shortcut.
After State Transitions
When you successfully call flow_update and the state changes (e.g. approval → ready), the MCP server's response tells you to re-call devflow_init. You must do this — the server's enforcement context resets on each state.
The .devflow-active file
The MCP server writes .devflow-active in the project root when devflow_init succeeds. Hooks use it to detect the current flow. Never edit it manually.
Error Recovery
- 403 Gate blocked: The flow is in a state that forbids this action. Check
/devflow-next, followallowedActions. - 400 Missing field: The response tells you which field. For
reviewtransitions:agentSummary+testingInstructionsare required. - Lease expired: Call
devflow_initagain to refresh the session lease.
Git Mode (DF-302)
Every devflow_init response includes a gitEnabled boolean (from git_settings.enabled). Behave accordingly:
gitEnabled: true— Project follows a git workflow. You MUST create branches, commit with Gitmoji, reportbranchName+commits[]viaflow_update, and ensure a merged PR beforereview → done.gitEnabled: false— Project does not enforce git. Do not rungit checkout -b, do not produce commits, do not callflow_update({ commits: [...] }), do not report a PR URL. Just edit files, run tests, and submitagentSummary + testingInstructionsfor review.
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 · 101 lines · 37 tokens per session scan A 58948685a371
devflow-core is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 1,419 once invoked, about $0.0002 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…