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-subagent-driven-devnpx skills add KlausFreiberufler/devflow-mcp --skill devflow-subagent-driven-devgit 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 | $0.00079 | $0.01449 |
| Opus 5 | $0.00039 | $0.00724 |
| Sonnet 5 | $0.00016 | $0.00290 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
devflow-subagent-driven-dev 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: devflow-subagent-driven-dev (DRAFT)
🚧 DRAFT — not yet active. This skill remains a draft even though the architecture is signed off. DF-427 (2026-05-22) closed all 7 open questions from the DF-424 RFC; the Iron Laws above are now authoritative. The skill stays
status: draftuntil the 8-flow Implementation Roadmap (seedocs/RFC_SUBAGENT_DF424.md→ "Closure (DF-427)") ships. Do not spawn sub-agents from real flows yet — the orchestrator-logic, worktree-extension, and aggregation code do not exist.
What this skill will do (eventually)
Take the implementation plan's task-list, classify each task by expected effort, and for tasks above a threshold (~5 minutes of agent work) spawn a fresh sub-agent in an isolated git-worktree. The sub-agent runs the task end-to-end (write tests, write code, commit) and reports completion back. The orchestrator-agent waits on all sub-agents, then merges the worktrees back to the flow's branch and submits for review.
Architecture (closed by DF-427)
All 7 open questions from DF-424 are resolved. The full Q→Decision mapping with reasoning and pseudocode lives in docs/RFC_SUBAGENT_DF424.md → "Closure (DF-427)". Summary:
- D1 (Spawn): Orchestrator-Agent calls Claude-Code
Agent-tool inline. - D2 (Isolation): Per-task git-worktree at
.claude/worktrees/<flowId>-task-<n>/. - D3 (Aggregation): Orchestrator merges sequentially in topo-dependency-order; semantic conflicts escalate to
task: blocked. - D4 (Failure): 3-retry pattern; orchestrator-takeover on retry-4; user-escalation if orchestrator also fails.
- D5 (Threshold): ≥ 5 estimated agent-minutes for sub-agent spawn. Configurable per project.
- D6 (Budget): 30k tokens hard-cap. Configurable per project. Budget-exhaust = orchestrator-takeover.
- D7 (Tokens): Orchestrator owns all flow-level discipline-tokens; sub-agents emit only per-task discovery-reports.
When this skill becomes active
This skill is marked status: draft and optional: true. RFC sign-off is done (DF-427). The skill will be promoted to active only after the 8-flow Implementation Roadmap completes:
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.
- yesterday First seen · 68 lines · 79 tokens per session scan A 20bc4b3d9904
devflow-subagent-driven-dev is a skill published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 1,449 once invoked, about $0.0004 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.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…