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/cskwork/supergoal-skill/archifynpx skills add cskwork/supergoal-skill --skill archifygit clone --depth 1 https://github.com/cskwork/supergoal-skillWhat 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 | $0.00039 | $0.05539 |
| Opus 5 | $0.00019 | $0.02769 |
| Sonnet 5 | $0.00008 | $0.01108 |
| Haiku 4.5 | $0.00004 | $0.00554 |
Grade A, and why
archify 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 2d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archify Skill
Create professional technical diagrams as self-contained HTML files with inline SVG, a theme toggle, and a built-in image/SVG export menu.
Every diagram ships with a dark/light theme toggle (persists in localStorage, respects prefers-color-scheme), an export menu (copy PNG to clipboard; download PNG/JPEG/WebP rasterized natively at up to 4× resolution; download a dual-theme SVG that follows the embedding host's prefers-color-scheme — ideal for GitHub READMEs), and a CSS-variable color system that keeps both themes consistent.
Setup
No dependency installation is required. The distributed skill includes standalone validators compiled from all five JSON Schemas, so schema and layout validation work immediately after installation. The generated HTML and the renderer runtime are both dependency-free.
Run node bin/archify.mjs doctor to verify an installation. Run node bin/archify.mjs demo [output-directory] to generate a ready-to-open example before creating the first custom diagram.
If you have no shell access at all (e.g. the skill was added as project knowledge), fall back to architecture mode for every request: hand-place SVG into assets/template.html following the Design System below, and run the self-review checklist before delivering.
Choosing a Diagram Type
| Type | Use for | How |
|---|---|---|
architecture |
System components, cloud resources, services, security boundaries, infrastructure | renderers/architecture/render-architecture.mjs + JSON (or hand-place SVG when renderers can't run) |
workflow |
Technical flows, approval gates, tool calls, runbooks, CI/CD, incident response | renderers/workflow/render-workflow.mjs + JSON |
sequence |
API call chains, request lifecycles, cache fallback, async traces, return paths | renderers/sequence/render-sequence.mjs + JSON |
dataflow |
Pipelines, ETL/ELT, PII isolation, lineage, warehouse sync, consumers | renderers/dataflow/render-dataflow.mjs + JSON |
lifecycle |
State machines, status transitions, wait states, retries, terminal states | renderers/lifecycle/render-lifecycle.mjs + JSON |
What ships with it
34 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.
- assets/template.html 50 KB
- bin/archify.mjs 8.1 KB runs code
- examples/agent-run.lifecycle.json 3.4 KB
- examples/agent-tool-call.workflow.json 5.2 KB
- examples/cache-miss-request.sequence.json 3.5 KB
- examples/product-analytics.dataflow.json 4.7 KB
- examples/web-app.architecture.json 2.9 KB
- LICENSE 1.1 KB
- package.json 661 B
- renderers/architecture/grid.mjs 2.0 KB runs code
- renderers/architecture/render-architecture.mjs 17 KB runs code
- renderers/dataflow/README.md 2.9 KB
- renderers/dataflow/render-dataflow.mjs 13 KB runs code
- renderers/lifecycle/README.md 3.8 KB
- renderers/lifecycle/render-lifecycle.mjs 17 KB runs code
- renderers/sequence/README.md 3.0 KB
- renderers/sequence/render-sequence.mjs 13 KB runs code
- renderers/shared/cli.mjs 2.1 KB runs code
- renderers/shared/generated-validators.mjs 226 KB runs code
- renderers/shared/geometry.mjs 7.5 KB runs code
- renderers/shared/layout-report.mjs 1015 B runs code
- renderers/shared/utils.mjs 3.8 KB runs code
- renderers/shared/validator.mjs 1.4 KB runs code
- renderers/workflow/README.md 4.2 KB
- renderers/workflow/render-workflow.mjs 20 KB runs code
- schemas/architecture.schema.json 3.9 KB
- schemas/common.schema.json 1.1 KB
- schemas/dataflow.schema.json 4.6 KB
- schemas/lifecycle.schema.json 5.1 KB
- schemas/README.md 3.4 KB
- schemas/sequence.schema.json 3.8 KB
- schemas/workflow.schema.json 6.9 KB
- scripts/check-render-output.mjs 8.6 KB runs code
- scripts/generate-validators.mjs 2.3 KB runs code
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.
- 2d ago First seen · 275 lines · 39 tokens per session scan A 48d67d07061c
archify is a skill published in the GitHub repository cskwork/supergoal-skill (4 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 5,539 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 2026-08-31.
Other skills, from other repositories
ingest-pipeline
The ingest pipeline's topic-tree plan format and confirmation gate, the opt-in destructive optimize (restructure) procedure, and the final-report template for claude-wiki-pages. Documents the plan/approval and restructure steps so the ingest agent can drive them without inlining the detail. Trigger when an agent or…
ingest
Ingest one or more sources from vault/raw/ into typed wiki pages under vault/wiki/. Trigger when the user says "ingest this source", "process the file I just dropped in raw/", "add this to the wiki", or invokes /claude-wiki-pages:ingest directly. Prefer the pipeline (/claude-wiki-pages:claude-wiki-pages-ingest-agent)…
curator-fixes
The curator's supplemental diagnostic checks, the nine safe auto-fixes, the automatic judgment-fix procedure, and the lint-report template for claude-wiki-pages. Documents what the curator checks and how it repairs wiki structure under a git checkpoint, so the curator agent can apply fixes without inlining the…
engine-api
The LLM-facing contract for the deterministic claude-wiki-pages Bun engine — how ANY agent should call it. Documents each subcommand (verify, fix, heal, doctor, config, migrate, search, snapshot; plus planned index/link-suggest), its --json output shape, exit codes, and when to call it on a write-path. Trigger when an…
init
Onboarding entry point. Scaffold a new LLM Wiki vault in the user's project by copying from the skill's own template/, stamp the schema version, and orient the user. Trigger when the user says "set up a wiki", "initialize the vault", "start a new LLM Wiki", "bootstrap the vault", or invokes /claude-wiki-pages:init…
lint
Read-only audit of vault/wiki/ for structural and provenance drift. Reports Errors, Warnings, and Info per the lint rules in vault/CLAUDE.md. Trigger when the user says "lint the vault", "audit the wiki", "check for broken links", "run a health check on the wiki", or invokes /claude-wiki-pages:lint directly. Does not…