workflow-router

workflow-router is a skill for Codex from Eliyce/paqad-ai. It costs 16 tokens per session (1,099 once invoked), scanned A, original, MIT.

A request router that matches a raw prompt to one approved project workflow before other processing begins.

In plain words
What is it for?
Use it at the start of every request to select and validate a workflow, including project-defined workflows, then produce the required YAML decision.
Why use it?
It prevents prompt aliases and spelling variants from being handled inconsistently, and stops when no supported workflow matches instead of guessing.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it at the start of every request to select and validate a workflow, including project-defined workflows, then produce the required YAML decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eliyce/paqad-ai/workflow-router
Install

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.

Any agent
npx skills add Eliyce/paqad-ai --skill workflow-router
Clone the repo
git clone --depth 1 https://github.com/Eliyce/paqad-ai

Made for: Codex.

Wrote 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.

agentmods badge for workflow-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/workflow-router/github.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/workflow-router)
Your own site
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/workflow-router"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/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.

agentmods 80×15 button for workflow-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/workflow-router"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/workflow-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01099
Opus 5 $0.00008 $0.00549
Sonnet 5 $0.00003 $0.00220
Haiku 4.5 $0.00002 $0.00110

Measured 10d ago against content hash c034e59e9c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/lint-output.sh, scripts/route-request.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

runtime/base/skills/workflow-router/SKILL.md · 178 lines

What it actually says

What It Does

Routes the incoming request into one canonical workflow before the pipeline starts so prompt aliases and typo variants live in skill content instead of hardcoded TypeScript checks.

Use This When

Use this first for every incoming request. If no routing rule matches, stop and return no workflow match instead of guessing.

Inputs

  • Read the raw request text first.
  • Check the canonical project profile only when it changes whether a matched workflow is valid.
  • Check project workflow templates when a rule targets custom:{workflow-name}.

Procedure

  1. Pipe the raw request into scripts/route-request.sh — it lowercase-normalizes, walks assets/routing-rules.txt (priority ordered, longest-pattern tiebreak), and emits the YAML decision.
  2. When a rule targets custom:{workflow-name}, the LLM confirms the template exists before returning it (script does not).
  3. Validate with scripts/lint-output.sh.

Output Contract

  • Match assets/output.template.yaml: workflow:, reason:, matched_rule: (or workflow: none + reason: only).
  • Output must pass scripts/lint-output.sh (exit 0).

Escalate / Stop Conditions

  • Do not invent a workflow when no rule matches.
  • Warn when a custom workflow target is missing from the project.

Resources

  • references/routing-rules.md
  • scripts/route-request.sh
  • scripts/lint-output.sh
  • assets/routing-rules.txt
  • assets/output.template.yaml
  • agents/openai.yaml
Files

What ships with it

6 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.

Changes

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.

  1. 10d ago First seen · 178 lines · 16 tokens per session scan A c034e59e9c88

Subscribe to this mod's changes

workflow-router is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,099 once invoked, about $0.0001 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 2026-08-31.