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-architecture-contrastWrote 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-architecture-contrast)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-architecture-contrast"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-architecture-contrast/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-architecture-contrast"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-architecture-contrast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.01357 |
| Opus 5.5 | $0.00020 | $0.00543 |
| Sonnet 5.5 | $0.00010 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
stelow-workflow-architecture-contrast 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Contrast
Use this skill during the existing Architecture stage. It does not create a new root stage and it does not own card state or execution lifecycle.
Method
- Read the approved Scope Map when one exists and record its version. Read
selected-interface.mdwhen one exists: the construction must serve the chosen interaction direction, never reinterpret it. - Write the decision question, fixed constraints, invariants that must hold regardless of direction, criteria, and missing evidence.
- Preserve the decision-maker's invariants before showing agent synthesis. A reference architecture cited here is provenance for a direction already named — never a source of new directions, because generating fresh options from a gallery would replace recorded invariants with the agent's browsing.
- Generate bounded directions with explicit trade-offs, reversibility notes, and compatibility with the approved scopes.
- Show trade-offs, evidence, missing evidence, and accepted sacrifice.
- Stop for a live question when the choice changes technical authority or cannot be made from current evidence.
- Emit a selection receipt only after a current answer or an explicit agent disposition. Then record the pick host-side with
scripts/stelow decide --selected <winner> --rejected <losers> --scopes <covered>— the JSON receipt is the brief's record, the host record is what binds future work. Never hand-writedecision-receipts.json; overturning a live pick needs an opened challenge (scripts/stelow decide --open-challenge --against <receipt> --reason <why>, then--challenge <challenge-id>).
Artifact contract
The recipe writes:
architecture/contrast.json— brief, directions, provenance, and disposition;architecture/architecture.md— readable rendering of the validated records.
The choice ask inside the Architecture stage remains the owner of the actual architecture pick. Architecture Contrast does not create a second choice stage or choice receipt.
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.
- 10d ago Changed · +1 lines c2170dc8e9d4
- 14d ago Changed · +49 lines a3bbf86790fe
- 28d ago Changed 9503df4ec8d9
- 29d ago Changed · +1 lines c2736d4cc8e1
- 1mo ago First seen · 71 lines · 49 tokens per session scan A 13935ccf4341
stelow-workflow-architecture-contrast is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 1,357 once invoked, about $0.0002 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 2026-10-04.
stelow-workflow-architecture-contrast compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-workflow-architecture-contrastcalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 49 | 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 |