Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/calionauta/stelownpx agentmods add skills/calionauta/stelow/stelow-workflow-shape-upWrote 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-shape-up)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-shape-up"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-shape-up/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-shape-up"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-shape-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.04537 |
| Opus 5.5 | $0.00026 | $0.01815 |
| Sonnet 5.5 | $0.00013 | $0.00907 |
| Haiku 4.5 | $0.00006 | $0.00454 |
Grade A, and why
stelow-workflow-shape-up 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 14d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape Up Planning
Tools: See
../stelow-workflow-orchestrator/references/cli-tools/subagents.mdfor subagent patterns.
Overview
This skill executes the Shape Up planning phase.
Standalone Quick Start
When loaded standalone (via /skill:stelow-workflow-shape-up), follow these steps in order:
1. shape:10 — Optional parallel recon (codebase context, brownfield only)
2. shape:12 — Tech preview (breadth-gated, codebase analysis)
3. shape:15 — Assumption Check (surface assumptions BEFORE shaping) ← DO NOT SKIP
4. shape:20 — Shaping
5. Proposal output with validation
Do NOT skip shape:15 (Assumption Check). It prevents generic requests from being shaped without validating core assumptions first. shape:10 is optional — for brownfield projects, it maps existing code context. For greenfield, skip straight to shape:12.
See the Input Detection section at the bottom for what to do on first load.
How to Load
Via Orchestrator (recommended)
The orchestrator reads this file directly when needed.
Standalone
This skill works standalone. Use the Input Detection section below to tell the skill what you want to shape. Follow the instructions inline.
shape:10 — Parallel Recon (optional)
Before shaping, launch subagent to map context:
Use the subagents tool (see ../stelow-workflow-orchestrator/references/cli-tools/subagents.md) in parallel for optional recon:
2 parallel scouts (fresh context):
1. Map current code state → context/current-state.md
2. Map technical risks → context/risks.md
Check for reshape context (from planning:15 Alignment Check):
BC="context/blocking-constraints.md"
if [ -f "$BC" ]; then
echo "RESHAPE_CONTEXT_FOUND"
cat "$BC"
fi
If blocking constraints exist from a previous tech planning cycle, read them BEFORE shaping — the new proposal must address these constraints. After reading, remove the file to prevent stale context in future cycles.
Read the outputs before proceeding.
What ships with it
8 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/cli-tools/cymbal.md 1.6 KB
- references/execution-guide.md 2.6 KB
- references/output-expectations.md 923 B
- references/proposal-structure.md 8.2 KB
- references/risk-analysis.md 2.3 KB
- references/shaping-complete.md 1.9 KB
- references/shaping-principles.md 1.8 KB
- references/tech-preview.md 5.7 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.
- 14d ago Changed · +6 lines 6fdcf3a3a731
- 18d ago Changed afbb2398beea
- 26d ago Changed 0adca8c82754
- 1mo ago Changed · -6 lines 1089061ca3d8
- 1mo ago Changed · +6 lines f58c408ea733
- 1mo ago Changed · +39 lines 3ac9cfa71dfc
- 1mo ago Changed · +5 lines 3d38741ccc86
- 1mo ago Changed · +11 lines d278bcefbaa8
- 1mo ago Changed · +3 lines de3effc087e5
- 1mo ago First seen · 402 lines · 64 tokens per session scan A 194a72423270
stelow-workflow-shape-up is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 4,537 once invoked, about $0.0003 per session on Opus 5.5. 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.
stelow-workflow-shape-up compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-workflow-shape-upcalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 64 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |