Borrowing it
Nothing to install: this file belongs to calionauta/stelow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/calionauta/stelow/main/AGENTS.mdgit 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/instructions/calionauta/stelow/agents-md)<a href="https://agentmods.dev/instructions/calionauta/stelow/agents-md"><img src="https://agentmods.dev/badge/instructions/calionauta/stelow/agents-md/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/instructions/calionauta/stelow/agents-md"><img src="https://agentmods.dev/badge/instructions/calionauta/stelow/agents-md.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 | $0.05216 | $0.05216 |
| Opus 5.5 | $0.02086 | $0.02086 |
| Sonnet 5.5 | $0.01043 | $0.01043 |
| Haiku 4.5 | $0.00522 | $0.00522 |
Grade C, and why
stelow AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **sem** ([Ataraxy-Labs/sem](https://github.com/Ataraxy-Labs/sem)) — entity-level diff for Execution Critique (functions, types, methods instead of raw lines). Cross-platform install: `curl -fsSL https://raw.githubuserc Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **sem** ([Ataraxy-Labs/sem](https://github.com/Ataraxy-Labs/sem)) — entity-level diff for Execution Critique (functions, types, methods instead of raw lines). Cross-platform install: `curl -fsSL https://raw.githubuserc How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stelow
Transform product ideas into approved, testable plans — systematically.
Project Overview
Type: Skills-only, host-agnostic product workflow library. The product is
30 portable agentskills-compatible skills (skills/stelow-product-* + skills/stelow-workflow-*) plus a
zero-dependency shell helper (scripts/stelow). There is no extension code,
no compiled plugin, and no per-host adapter in the repo.
Stack: bash + python3 (runtime), Node 20+, TypeScript strict (tooling/tests).
Hosts: any agent that reads ~/.agents/skills/<name>/SKILL.md (the
agentskills.io standard) — Claude Code, Codex, Cursor, OpenCode, Gemini CLI,
Goose, and other Agent Skills-compatible hosts.
Architecture
See architecture.md for module layout, data flow, and how to
extend. The 18-stage state machine is defined in
skills/stelow-workflow-orchestrator/stages.yaml (single source of truth);
skills/stelow-workflow-orchestrator/references/transitions.md is the
data-only mirror that scripts/stelow advance and the router validate against
(regenerate from stages.yaml — do not edit by hand). Visual review gates
(gate, int-gate, plan-gate, diff-gate) are conditional by review mode —
see stages.yaml.
Building a visual host plugin (board/inbox/workers)? Read
docs/host-plugin-blueprint.md first — the
extracted lifecycle, inbox, ask/answer, sync, and UI rules with the
bb-plugin-stelow file mapping.
Top-level layout
| Directory | Purpose |
|---|---|
skills/stelow-workflow-entry/ |
Entry point: intent classification, state.md scaffold, first-stage selection (loaded when STELOW_WORKFLOW=1). |
skills/stelow-workflow-router/ |
Router: validate next candidate, advance via helper, load next stage, append hand-off audit. |
skills/stelow-workflow-orchestrator/ |
Orchestrator + stages.yaml + stages/*.md + references/transitions.md. |
skills/stelow-product-*/ + skills/stelow-workflow-*/ |
The other 27 self-contained skills (12 stage/execution workflow + 15 product). |
scripts/stelow |
Portable CLI: status, advance, doctor, seed, schema, check, ask (lock + TTL, invariants). The breadboard rules live here so every environment that runs the workflow can run them. |
scripts/render-diagram.mjs + scripts/breadboard-mermaid.mjs + scripts/breadboard-markdown.mjs |
Breadboard map → Mermaid → SVG/HTML/markdown views. Repo-side tooling (not installed by install.sh); the map JSON is the artifact, the views are projections. Validation is stelow check breadboard, not this. |
types/stages.ts |
Stage-model TS interfaces mirroring stages.yaml. |
stelow.schema.json / stelow.json |
Workflow tracking schema + per-project runtime state. |
tests/ |
Vitest: unit/ + integration/ + skills/ contract tests. |
docs/design/, docs/agents-md-refs/ |
Historical design docs + agent reference notes. |
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 · +4 lines · +385 tokens per session 727ba59d82fc
- 18d ago Changed · -5 tokens per session aef65c30ff45
- 1mo ago Changed · -1 lines · +32 tokens per session 1d9095355cde
- 1mo ago Changed · +1 lines · +82 tokens per session ab728c357d18
- 1mo ago Changed · +15 lines · +307 tokens per session afd15aae2bff
- 1mo ago Changed · +49 tokens per session bb1e17c12518
- 1mo ago Changed · -3 lines · -91 tokens per session f2eba060ba12
- 1mo ago Changed · +5 lines · +110 tokens per session 86e97e07ea65
- 1mo ago Changed · +5 lines · +61 tokens per session 3cd556b15b6b
- 1mo ago First seen · 238 lines · 4,286 tokens per session scan C 2c1e2848acbd
stelow AGENTS.md is an instructions file published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 5,216 tokens to every session, about $0.0209 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
stelow AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow AGENTS.mdcalionauta/stelow | Instructions file | 14 | 9d ago | MIT | C | 5,216 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |