cortex-wiki-author

cortex-wiki-author is a skill for Claude Code, Codex from cdeust/Cortex. It costs 98 tokens per session (1,116 once invoked), scanned A, original, MIT.

A documentation skill for writing permanent wiki pages alongside Cortex memory. It covers architecture decision records, specifications, file documentation, and notes, which are longer documents about how a project works or why a decision was made.

In plain words
What is it for?
Use it to record architecture decisions, write specifications, document files, create project notes, and link related wiki pages.
Why use it?
It keeps important decisions and explanations in authored pages that are not automatically removed, while also making them discoverable through Cortex memory.

Skill for Claude CodeCodex

Part of the hypermnesia-mcp plugin — 13 skills, 3 commands, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/cdeust/cortex/cortex-wiki-author
Any agent
npx skills add cdeust/Cortex --skill cortex-wiki-author
Clone the repo
git clone --depth 1 https://github.com/cdeust/Cortex

Made for: Claude Code, Codex.

Or install hypermnesia-mcp, the plugin that ships this one along with the rest of its 13 skills, 3 commands, 2 MCP servers.

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 cortex-wiki-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdeust/cortex/cortex-wiki-author.svg)](https://agentmods.dev/skills/cdeust/cortex/cortex-wiki-author)
Your own site
<a href="https://agentmods.dev/skills/cdeust/cortex/cortex-wiki-author"><img src="https://agentmods.dev/badge/skills/cdeust/cortex/cortex-wiki-author.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00098 $0.01116
Opus 5 $0.00049 $0.00558
Sonnet 5 $0.00020 $0.00223
Haiku 4.5 $0.00010 $0.00112

Measured 3d ago against content hash 68fde7023ef1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-wiki-author 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 3d 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.

skills/cortex-wiki-author/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.

Wiki Author — Long-form Documentation Layer

Keywords

adr, spec, decision, design doc, rfc, file doc, notes, wiki, documentation, link pages, bidirectional link, supersedes, implements, depends on

Overview

Cortex's wiki is a Markdown authoring surface for the long-form artifacts that don't fit the thermodynamic memory model: architecture decision records, specs, per-file documentation, and free-form notes. Pages live under ~/.claude/methodology/wiki/ and are never pruned — they are first-class authored content, not derived views. Every write also registers a protected pointer memory in PostgreSQL so recall surfaces wiki pages alongside regular memories.

Use this skill when: the user is making a decision that should persist, finalizing a spec, documenting a file's purpose, or asking for two wiki pages to be linked.

Do NOT use for: ephemeral facts (use remember), domain profiles (use query_methodology), or regenerating documentation from memory (the wiki is authored, not projected).

Workflow

Record an architecture decision

cortex:wiki_adr({
  "title": "Use pgvector for retrieval",
  "context": "We need a searchable memory store with hybrid ranking.",
  "decision": "Adopt PostgreSQL + pgvector + pg_trgm as the single backend.",
  "consequences": "No SQLite fallback. Operator must provision Postgres 15+.",
  "status": "accepted",
  "tags": ["storage", "retrieval"]
})

Returns { path, number, title, status, ... }. ADR numbers auto-increment.

Write a spec

cortex:wiki_write({
  "path": "specs/wiki-authoring.md",
  "content": "# Wiki authoring\n\n## Summary\n\nClaude authors ADRs and specs during sessions..."
})

Pass the final markdown you want to land. Use "mode": "append" to add to an existing page, "replace" to overwrite.

Document a file

cortex:wiki_write({
  "path": "files/mcp_server-handlers-wiki_write.md",
  "content": "# `mcp_server/handlers/wiki_write.py`\n\n## Purpose\n\nComposition root for the wiki authoring tool..."
})

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. 3d ago First seen · 107 lines · 98 tokens per session scan A 68fde7023ef1

Subscribe to this mod's changes

cortex-wiki-author is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,116 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

preregister

Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when…

pedrohcgs/claude-code-my-workflow · 153 tokens

data-analysis

End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use when user says "analyze this dataset", "run a regression on X", "explore this CSV", "full analysis workflow", "get me summary stats and a regression", or points at a .csv/.rds/.dta and asks for…

pedrohcgs/claude-code-my-workflow · 104 tokens

extract-tikz

Extract TikZ diagrams from Beamer .tex source, compile each to a standalone PDF, and convert to SVG with 0-based indexing. Use when user says "extract the tikz", "regenerate the diagrams", "rebuild the SVGs", "sync tikz to quarto", or after editing TikZ blocks in a Beamer deck that also has a Quarto mirror.

pedrohcgs/claude-code-my-workflow · 83 tokens

qa-quarto

Adversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML render to the Beamer PDF benchmark for content/visual parity; a fixer agent applies fixes; loops until APPROVED (max 5 rounds). Use when user says "qa the quarto", "check parity", "does the html match the pdf?", "quarto matches beamer?"…

pedrohcgs/claude-code-my-workflow · 105 tokens

compile-latex

Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a .tex file isn't producing a PDF. Operates on Slides/.tex.

pedrohcgs/claude-code-my-workflow · 73 tokens

fin-paper-convert

Compile LaTeX to PDF and convert to target journal format.

csmar432/finai-research · 12 tokens