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-routergit 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-router)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-router"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-router/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-router"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-router.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 | $0.00073 | $0.00765 |
| Opus 5 | $0.00036 | $0.00382 |
| Sonnet 5 | $0.00015 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
stelow-workflow-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Router
The router is the workflow control plane. It runs once per stage transition. It does not implement any stage logic itself; it only moves state forward and loads the next stage skill.
Contract
Input:
state.md(workflow state withcurrent_stageset)- The previous skill's
## Hand-off (workflow mode)block STELOW_WORKFLOW=1+STELOW_STATE=<path-to-state.md>markers
Output:
state.mdadvanced (viascripts/stelow advance <next-candidate>)- The next stage's
SKILL.mdloaded for the next agent turn - A new
## Hand-off (router)block appended tostate.md
Algorithm
# 1. Read current_stage and the previous skill's Hand-off block.
current=$(scripts/stelow status --json | jq -r .current_stage)
next=$(extract_hand_off_field next-candidate)
# 2. Validate next against transitions.md.
transitions=skills/stelow-workflow-orchestrator/references/transitions.md
allowed=$(awk "/^### $current\$/,/^### |\$/" "$transitions" \
| grep -E "^(next|accept|rework):" \
| head -1 | awk "{print \$2}" | tr -d "[],\"")
if ! echo "$allowed" | grep -qw "$next"; then
echo "router: rejected '$next' (allowed from $current: $allowed)"
# rework path: return to previous stage
prev=$(echo "$allowed" | head -1)
scripts/stelow advance "$prev"
load_skill "$prev"
exit 1
fi
# 3. Advance state and load next stage.
scripts/stelow advance "$next"
# 4. Append router Hand-off (audit).
cat >> "$STELOW_STATE" <<EOF
## Hand-off (router) — $(date -Iseconds)
from : $current
to : $next
skill loaded: stelow-product-$next
EOF
Reject / rework path
If next is not in the allowed list:
- Default behavior: advance to the first
reworkcandidate (or therejectcandidate if no rework is defined) so the workflow can recover without manual intervention. - Record the rejection in
state.mdbody so the next agent can see why it was bounced.
Total load budget
≤ 5k tokens (per SCOPE-4 NFR). No domain logic, no copy from stage skills — just the algorithm above plus the conventions below.
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.
- 3d ago Changed · -2 tokens per session 7734abb3bc6a
- 8d ago First seen · 91 lines · 75 tokens per session scan A 9da644de8482
stelow-workflow-router is a skill published in the GitHub repository calionauta/stelow (10 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 765 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 2026-09-04.
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…