nulang: Skill for Claude Code

.claude/skills/wiki-updater/SKILL.md

wiki-updater is a skill for Claude Code from nulang-org/nulang. It costs 148 tokens per session (2,210 once invoked), scanned A, original, Apache-2.0.

An in-repository wiki for recording how a codebase works. It keeps information from source files, specifications, design documents, and other references in linked Markdown pages.

In plain words
What is it for?
Use it to create, update, refresh, and check wiki pages when documenting a subsystem, adding a reference, or answering questions about the codebase.
Why use it?
It reduces the need to rediscover how the codebase works after changes or new questions. It also keeps knowledge in the repository instead of leaving it scattered across conversations and documents.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is nulang-org/nulang's own configuration. It tells Claude Code how to work on nulang itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nulang configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nulang-org/nulang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nulang-org/nulang/main/.claude/skills/wiki-updater/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nulang-org/nulang

Made for: Claude Code.

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 wiki-updater

README.md
[![agentmods](https://agentmods.dev/badge/skills/nulang-org/nulang/wiki-updater/github.svg)](https://agentmods.dev/skills/nulang-org/nulang/wiki-updater)
Your own site
<a href="https://agentmods.dev/skills/nulang-org/nulang/wiki-updater"><img src="https://agentmods.dev/badge/skills/nulang-org/nulang/wiki-updater/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 wiki-updater

Your own site · 80×15
<a href="https://agentmods.dev/skills/nulang-org/nulang/wiki-updater"><img src="https://agentmods.dev/badge/skills/nulang-org/nulang/wiki-updater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,210 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 $0.00148 $0.02210
Opus 5 $0.00074 $0.01105
Sonnet 5 $0.00030 $0.00442
Haiku 4.5 $0.00015 $0.00221

Measured 11d ago against content hash a5d45ae4f503, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

wiki-updater 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 11d 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.

.claude/skills/wiki-updater/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nulang Wiki Curator

You are the maintainer of Nulang's in-repo knowledge base at wiki/. This skill instantiates Andrej Karpathy's llm-wiki.md pattern for a source-code repository: the wiki is a persistent, compounding artifact that grows richer with every source ingested and every question asked. You (the LLM) do all the writing; the human curates sources and directs the analysis.

Layers

  • Raw sourcessrc/*.rs, SPEC2.md, AGENTS.md, RFC/*.md, GOVERNANCE.md, CHANGELOG.md, and any external design docs the user drops in. Immutable to you: never modify code or spec files as part of a wiki operation.
  • The wikiwiki/*.md. You own this layer entirely. Create pages, update them when sources change, maintain cross-references (Obsidian-style [[wiki-links]]), keep everything consistent.
  • The schema — this file (SKILL.md) plus AGENTS.md. Co-evolve the conventions here as the wiki matures.

Conventions

  • Filenames: kebab-case.md. One page per concept, entity, subsystem, or source.
  • Categories (also directory prefixes when useful):
    • overview/architecture-overview.md, compiler-pipeline.md, high-level maps.
    • subsystems/ — one page per major subsystem (VM, JIT, runtime, WASM backend, AOT backend, AI runtime, LSP, Python interop, FFI, package manager, format layer).
    • concepts/ — one page per conceptual entity (capability lattice, effect rows, ORCA GC, NaN-tagging, work-stealing scheduler, gossip membership, delta CRDTs, non-blocking LLM suspend).
    • opcodes/ — one page per opcode group (or a single bytecode-opcodes.md for the full table).
    • sources/ — summaries of ingested external docs (RFCs, blog posts, design notes) with ## Source metadata block up top.
    • queries/ — filed answers to user questions worth preserving.
  • Cross-references: Obsidian-style [[architecture-overview]] links between wiki pages. Source citations use path:line (or path:start-end for ranges) referencing files in the repo — never bare filenames.
  • Frontmatter (optional but useful): YAML block with updated:, sources: (list of path:line refs), tags:. Enables Dataview-style queries later.
  • Style: Match Nulang's terse, evidence-first tone. Every claim MUST be grounded in a source citation. No marketing language. Prefer bullet lists over prose walls.
  • Length: Pages should be scannable — one screen ideally, three max. Deep detail lives in cross-referenced sub-pages, not walls of text.

Read the full file on GitHub · 107 lines

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. 11d ago First seen · 107 lines · 148 tokens per session scan A a5d45ae4f503

Subscribe to this mod's changes

wiki-updater is a skill published in the GitHub repository nulang-org/nulang (5 stars, last pushed today), licensed Apache-2.0. It adds 148 tokens to every session and 2,210 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

review-agent-memory

This skill reviews agent memory and state-store configuration for correctness. Use this skill when the user asks to "review agent memory", "check state store config", "audit agent persistence", or similar.

diagrid-labs/dapr-skills · 43 tokens

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens