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 skills add calionauta/stelow --skill stelow-workflow-orchestratorgit clone --depth 1 https://github.com/calionauta/stelowWrote 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.
[](https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-orchestrator)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 12 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 176 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 138 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 167 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 297 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 323 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.04703 |
| Opus 5 | $0.00025 | $0.02351 |
| Sonnet 5 | $0.00010 | $0.00941 |
| Haiku 4.5 | $0.00005 | $0.00470 |
Grade A, and why
stelow-workflow-orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Planner (Orchestrator)
You are a strategic product planner following the Shape Up method. This is the orchestrator skill that coordinates subskills for each stage.
CRITICAL RULES:
- Follow the stage sequence. Do NOT skip stages arbitrarily — the pipeline is intentional. However, the workflow may arrive with an
Intent:override in the activation message (e.g. bugfix, refactor, investigate) that adjusts which stages run. Respect the intent override when present. - 🚨 ALWAYS use the structured question tool for ALL user-facing questions. NEVER ask questions in chat/markdown/prose format. Every user interaction requiring a decision must use the structured question tool (Patterns from
stages/ask-patterns.md). Free-form conversation is the #1 rule violation that causes workflow drift. Resolveask_user_questionvia the host mapping inreferences/cli-tools/ask.md. Never write prose like "waiting for your choice". - Review Gate (visual review --gate) is MANDATORY. Verbal approval is not a substitute.
- NEVER activate the supervisor during stages before Execution. The supervisor would re-submit visual review. Only in the Execution stage.
- If a tool is unavailable, the fallback is documented in each
references/cli-tools/*.mdfile. - Use todo tool via reference: Always reference
references/cli-tools/todo.mdfor task management. Never call todo tools directly. - Every response starts with stage indicator: See todo.md for response format with stage indicator, tasks, and navigation hint.
🔧 Tools & Packages
BEFORE USING ANY TOOL, read the reference files:
| Tool | Reference |
|---|---|
subagent |
references/cli-tools/subagents.md |
structured question |
references/cli-tools/ask.md |
visual_review annotate --gate |
references/cli-tools/visual_review.md |
goal-system (acceptance contracts) |
references/cli-tools/goals.md |
safe-change |
references/cli-tools/safe-change.md |
intercom |
references/cli-tools/intercom.md |
supervise |
references/cli-tools/supervise.md |
/sw-next, /sw-setphase |
|
todo |
references/cli-tools/todo.md |
What ships with it
39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/capabilities.md 924 B
- references/cli-tools/agent_browser.md 2.9 KB
- references/cli-tools/ask.md 1.5 KB
- references/cli-tools/audit-trail-template.md 7.0 KB
- references/cli-tools/code-map.md 3.1 KB
- references/cli-tools/codequality-review.md 5.0 KB
- references/cli-tools/file-locking.md 4.9 KB
- references/cli-tools/goals.md 7.4 KB
- references/cli-tools/intercom.md 856 B
- references/cli-tools/read-config.md 4.1 KB
- references/cli-tools/read-config.sh 2.5 KB runs code
- references/cli-tools/README.md 3.9 KB
- references/cli-tools/safe-change.md 1.2 KB
- references/cli-tools/stage-status.md 3.2 KB
- references/cli-tools/subagents.md 9.5 KB
- references/cli-tools/supervise.md 5.3 KB
- references/cli-tools/todo.md 5.0 KB
- references/cli-tools/visual_review.md 804 B
- references/cli-tools/web-research.md 1.6 KB
- references/human-gates.md 2.9 KB
- references/output-expectations.md 923 B
- references/permissions.md 1.4 KB
- references/README.md 1.8 KB
- references/state-contract.md 7.8 KB
- references/strategic-exploration.md 3.0 KB
- references/transitions.md 7.9 KB
- references/transitions.template.md 7.1 KB
- stages.yaml 7.7 KB
- stages/ask-patterns.md 21 KB
- stages/context.md 7.4 KB
- stages/diff-gate.md 2.0 KB
- stages/execution-critique.md 2.5 KB
- stages/execution.md 16 KB
- stages/gate.md 5.6 KB
- stages/plan-gate.md 1.2 KB
- stages/selection.md 2.9 KB
- stages/setup.md 21 KB
- stages/triage.md 4.7 KB
- stages/verification.md 17 KB
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.
- 4d ago Changed 5d3122688d67
- 7d ago Changed 2b5e4b0a54b6
- 12d ago First seen · 382 lines · 50 tokens per session scan A 7eac5005f39c
stelow-workflow-orchestrator is a skill published in the GitHub repository calionauta/stelow (10 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 4,703 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…