journey-synthesis

journey-synthesis is a skill for Codex from Eliyce/paqad-ai. It costs 47 tokens per session (636 once invoked), scanned A, original, MIT.

A journey planner that proposes a small number of goal-focused paths through a verified application map. Each journey describes one actor, one goal, ordered steps, branches, and possible outcomes.

In plain words
What is it for?
Use it to propose important user flows based on the map, tests, analytics, or project documentation.
Why use it?
It turns a list of screens and transitions into understandable user tasks while keeping suggestions separate from human-approved journeys.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to propose important user flows based on the map, tests, analytics, or project documentation.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/journey-synthesis"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/journey-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 636 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 $0.00047 $0.00636
Opus 5 $0.00023 $0.00318
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00005 $0.00064

Measured 9d ago against content hash 63c472c9506d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

journey-synthesis 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 9d 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.

runtime/capabilities/coding/skills/journey-synthesis/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What It Does

Turns the verified map into a few important journeys — the goal-directed paths an actor takes through the surfaces. Proposes at most the configured cap, each a well-formed arc42-style journey (one actor, one goal, ordered steps, branches, dual ends), and marks every one proposed. It never confirms a journey and never touches the graph layers; humans confirm through the audited surface.

Use This When

Use this after the map is assembled and verified, when the user wants journeys (not just the surface map). Skip it when the map itself is still incomplete — journeys compose surfaces that must already exist.

Inputs

  • The compiled app-map.yaml (surfaces, transitions, guards).
  • Signals that a path matters: tests, analytics, README hints.
  • Read references/journey-shape.md before proposing a journey.

Procedure

The journey shape is script-lintable; your job is choosing which few paths matter and grounding each step.

  1. Digest the hints (tests, analytics, README) for the paths that carry real user value.
  2. Propose at most the configured cap: each journey names one actor, one goal, an entry, ordered steps (surface + action + expectation), branches, and dual ends; every step references an existing surface (and, where it moves, an existing transition). Mark each proposed.
  3. Write the journey files to docs/site-map/journeys/<id>.journey.yaml and re-run paqad-ai sitemap run so the engine lints each journey's shape and step references.

Output Contract

  • A JSON object { journeys: [{ id, actor, goal, entry, steps, ends, status, evidence }], over_cap: [...] }.
  • status is proposed for every synthesized journey — never confirmed.
  • Every step references an existing surface id; the journey count never exceeds the cap.

Escalate / Stop Conditions

  • Never mark a journey confirmed; that is a human decision through the audited surface.
  • Never invent a surface to make a journey flow — a missing surface is a gap for the app-cartographer, not a step to fabricate.
  • Propose few, important journeys over an exhaustive dump; when over the cap, drop the least load-bearing and say why.

Read the full file on GitHub · 68 lines

Files

What ships with it

2 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. 9d ago First seen · 68 lines · 47 tokens per session scan A 63c472c9506d

Subscribe to this mod's changes

journey-synthesis is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 636 once invoked, about $0.0002 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 2026-09-03.