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 agentmods add skills/jlifyio/wyx/mapnpx skills add jlifyio/wyx --skill mapgit clone --depth 1 https://github.com/jlifyio/wyxWhat 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 | $0.00060 | $0.03487 |
| Opus 5 | $0.00030 | $0.01743 |
| Sonnet 5 | $0.00012 | $0.00697 |
| Haiku 4.5 | $0.00006 | $0.00349 |
Grade A, and why
map 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 yesterday.
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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Map Generation
Generate an architecture map — a synthesized view of all concept, pipeline,
and sync specs in a project. The map shows how concepts relate to each other, where data
flows, and which external systems are involved. It produces a single ARCHITECTURE.md
with a Mermaid relationship graph, dependency matrix, and data flow paths. ARCHITECTURE.md is a human reference document for orientation and code review — it is not consumed by wyx hooks.
How to interpret $ARGUMENTS
Determine the mode from the argument:
- Path (e.g.
src/lib/server/): Scoped mode — only map specs found under this path. Useful for mapping a subsystem without noise from unrelated modules. - No arguments: Full project mode — find and map all wyx specs across the entire project. This is the most common usage. For projects with 15+ concepts, recommend scoped mode to keep the graph readable.
- Zero specs found: Output "No wyx specs found. Run
/wyx:conceptfirst to create your first spec." and stop.
Pre-check: Skip if Clean
Before reading all specs, check if regeneration is needed:
- If
ARCHITECTURE.mdexists in the target directory, compare its modification time against all spec files - Use
find . -name "CONCEPT.md" -o -name "PIPELINE.md" -o -name "SYNCS.md" -newer ARCHITECTURE.md(scoped to path if given) to find specs modified since last generation - If no spec file is newer, report: "ARCHITECTURE.md is up to date (generated: [date], no spec changes since)" and stop
- If any spec file is newer, run this section-level comparison — skip only after actually performing it, never as a blind skip:
- Read only the graph-contributing sections of the changed specs:
## interactions,## dependencies,## data boundary,## coordination graph, and PIPELINE.md's## purpose. These are exactly the graph-derivation sources in Step 2 — the set is intentionally identical so a skip never silences a real graph change. - Compare the text of those sections via
git diff— a textual comparison, never a rendered-graph judgment. Byte-identical watched text guarantees an identical derived graph. - If the watched text changed, or
ARCHITECTURE.mddoesn't exist, proceed to Step 1. - If byte-identical: insert or update a
> Verified current on [today's date]line immediately below the> Generated byheader inARCHITECTURE.md. Leave the> Generated byline untouched — the graph was not regenerated, only re-confirmed. This edit bumps the file's mtime so the SessionStart staleness warning stops re-firing every session. - Report: "ARCHITECTURE.md is up to date (graph sections unchanged — verified current [today's date])" and stop.
- Read only the graph-contributing sections of the changed specs:
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.
- yesterday First seen · 205 lines · 60 tokens per session scan A 86d148f90855
map is a skill published in the GitHub repository jlifyio/wyx (3 stars, last pushed 23d ago), licensed MIT. It adds 60 tokens to every session and 3,487 once invoked, about $0.0003 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.
Other skills, from other repositories
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.
truecourse-list
List TrueCourse violations found in this repository.
code-quality-review
Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查, 可维护性审查, or comments about whether the change stays easy to…
cognitive-interface-audit
Comprehensive cognitive interface audit with two modes and a single tier. Planning mode designs task models, user expertise mapping, and error tolerance strategy. Audit mode evaluates mental model alignment (Norman's Gulfs), consistency (Gestalt), error tolerance (Wood 7-layer defense), cognitive load (NASA-TLX…