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/rudycity/superagent/codebase-wiki-generatornpx skills add RudyCity/superagent --skill codebase-wiki-generatorgit clone --depth 1 https://github.com/RudyCity/superagentWrote 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/rudycity/superagent/codebase-wiki-generator)<a href="https://agentmods.dev/skills/rudycity/superagent/codebase-wiki-generator"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/codebase-wiki-generator.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.04345 |
| Opus 5 | $0.00037 | $0.02173 |
| Sonnet 5 | $0.00015 | $0.00869 |
| Haiku 4.5 | $0.00007 | $0.00434 |
Grade A, and why
codebase-wiki-generator 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 4d 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Wiki Generator & Auto-Sync Suite (codebase-wiki-generator)
Provides an enterprise-grade, multi-dimensional methodology and automated tooling to generate, structure, validate, and automatically synchronize comprehensive codebase documentation and architecture wikis across Single Repositories or Multi-Workspace Federated Ecosystems (e.g. smart-seller + laris.click + shared modules).
When to Use This Skill
1. Creation & Initial Scaffolding
- Indonesian: "buat wiki codebase", "buat dokumentasi proyek", "scaffold wiki arsitektur", "bikin dokumentasi lengkap codebase", "generate wiki sistem", "buat multi workspace wiki", "federated wiki".
- English: "create codebase wiki", "generate project documentation", "scaffold architecture wiki", "build comprehensive codebase docs", "multi workspace wiki", "federated wiki".
2. Automatic & Incremental Update on Changes
- Indonesian: "update wiki tiap ada perubahan", "sync wiki dengan codebase", "update dokumentasi API", "perbarui diagram ERD di wiki", "pantau perubahan dan update wiki otomatis", "sync multi workspace".
- English: "update wiki on changes", "sync wiki with code", "update API documentation in wiki", "refresh ERD in wiki", "watch codebase and auto-sync wiki", "sync multi workspace".
3. Auditing & Link Validation
- Indonesian: "cek kesehatan link wiki", "validasi dokumentasi wiki", "audit kelengkapan wiki".
- English: "validate wiki links", "audit wiki completeness", "check broken links in docs".
Multi-Workspace & Federated Wiki Architecture
The wiki suite natively supports declarative configuration via docs/wiki/wiki-config.json:
{
"wikiDir": "docs/wiki",
"title": "Smart Seller & laris.click Federated Technical Wiki",
"primaryWorkspace": {
"name": "smart-seller",
"displayName": "Smart Seller (Core Platform & Store Assistant)",
"path": ".",
"routes": ["apps/api/src/routes", "apps/api/src"],
"schemas": ["packages/db/src/migrations", "packages/db/src"]
},
"federatedWorkspaces": [
{
"name": "laris.click",
"displayName": "laris.click (Checkout, SSO & Subscriptions Gateway)",
"path": "D:/backup from pc asus/Documents Development/laris.click",
"routes": ["backend/src/routes", "backend/src"],
"schemas": ["backend/src/db/migrations", "backend/src/db"]
}
]
}
What ships with it
23 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.
- examples/sample-wiki-structure.md 3.5 KB
- references/auto-sync-impact-rules.md 2.4 KB
- references/c4-diagram-guidelines.md 2.0 KB
- references/domain-driven-mapping.md 2.6 KB
- references/wiki-structure-standard.md 1.8 KB
- scripts/ai-sync-summarizer.cjs 5.1 KB runs code
- scripts/extract-api-catalog.cjs 12 KB runs code
- scripts/extract-db-erd.cjs 10 KB runs code
- scripts/generate-wiki-scaffold.cjs 12 KB runs code
- scripts/setup-git-hooks.cjs 2.6 KB runs code
- scripts/sync-wiki-on-change.cjs 14 KB runs code
- scripts/sync-wiki-to-rmemory.cjs 3.6 KB runs code
- scripts/validate-wiki-freshness.cjs 2.9 KB runs code
- scripts/validate-wiki-links.cjs 4.6 KB runs code
- scripts/watch-and-sync.cjs 10 KB runs code
- templates/00-index.template.md 2.7 KB
- templates/01-architecture-overview.template.md 4.4 KB
- templates/02-domain-models-and-data.template.md 5.1 KB
- templates/03-api-and-contracts.template.md 4.0 KB
- templates/04-features-and-workflows.template.md 4.4 KB
- templates/05-infrastructure-and-devops.template.md 3.1 KB
- templates/06-developer-onboarding.template.md 2.8 KB
- templates/07-adrs-and-decisions.template.md 2.9 KB
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.
- 4d ago First seen · 396 lines · 74 tokens per session scan A 6179ae9fbd73
codebase-wiki-generator is a skill published in the GitHub repository RudyCity/superagent (20 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 4,345 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…