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 Eliyce/paqad-ai --skill journey-synthesisgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/journey-synthesis)<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.
<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>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 | $0.00047 | $0.00636 |
| Opus 5 | $0.00023 | $0.00318 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
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.
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.mdbefore proposing a journey.
Procedure
The journey shape is script-lintable; your job is choosing which few paths matter and grounding each step.
- Digest the hints (tests, analytics, README) for the paths that carry real user value.
- 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. - Write the journey files to
docs/site-map/journeys/<id>.journey.yamland re-runpaqad-ai sitemap runso 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: [...] }. statusisproposedfor every synthesized journey — neverconfirmed.- 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.
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.
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.
- 9d ago First seen · 68 lines · 47 tokens per session scan A 63c472c9506d
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.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.