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.
git clone --depth 1 https://github.com/witt3rd/claude-pluginsWrote 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/commands/witt3rd/claude-plugins/expand-graph)<a href="https://agentmods.dev/commands/witt3rd/claude-plugins/expand-graph"><img src="https://agentmods.dev/badge/commands/witt3rd/claude-plugins/expand-graph/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.
<a href="https://agentmods.dev/commands/witt3rd/claude-plugins/expand-graph"><img src="https://agentmods.dev/badge/commands/witt3rd/claude-plugins/expand-graph.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00011 | $0.04608 |
| Opus 5.5 | $0.00004 | $0.01843 |
| Sonnet 5.5 | $0.00002 | $0.00922 |
| Haiku 4.5 | $0.00001 | $0.00461 |
Grade A, and why
expand-graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 731 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expand Graph
Discover missing relationships between a note and the rest of the knowledge graph through multi-strategy analysis.
0. Locate AZKG Repository
Check for AZKG_REPO_PATH environment variable:
- Use bash conditional:
if [ -z "$AZKG_REPO_PATH" ]; then REPO_PATH=$(pwd); else REPO_PATH="$AZKG_REPO_PATH"; fi - If AZKG_REPO_PATH is set: Use that path as the repository root
- If AZKG_REPO_PATH is not set: Use current working directory (pwd)
- Store result as REPO_PATH for all subsequent file operations
All file operations must use REPO_PATH:
- Read:
Read(REPO_PATH/filename.md)orRead("$REPO_PATH/filename.md") - Write:
Write(REPO_PATH/filename.md)orWrite("$REPO_PATH/filename.md") - Edit:
Edit(REPO_PATH/filename.md)orEdit("$REPO_PATH/filename.md") - Grep:
Grep(pattern, path=REPO_PATH)or with explicit path - Glob:
Glob(pattern, path=REPO_PATH)or with explicit path
Example usage:
# Check environment variable
if [ -z "$AZKG_REPO_PATH" ]; then
REPO_PATH=$(pwd)
else
REPO_PATH="$AZKG_REPO_PATH"
fi
# Then use REPO_PATH for all operations
Read("$REPO_PATH/agents.md")
Concrete examples:
- If AZKG_REPO_PATH="/c/Users/dothompson/OneDrive/src/witt3rd/donald-azkg" → Read("/c/Users/dothompson/OneDrive/src/witt3rd/donald-azkg/agents.md")
- If AZKG_REPO_PATH is not set and pwd is /c/Users/dothompson/OneDrive/src/witt3rd/donald-azkg → Read("agents.md") or use full path from pwd
1. Parse Input and Load Note
Input format: User provides:
- A note name:
/expand-graph mcp_security.md - Or just the topic:
/expand-graph mcp_security
Normalize and validate:
- Add
.mdextension if missing - Use Glob to verify the target note exists
- If not found, suggest similar notes using Glob
Read the target note:
- Use Read tool to get full content
- Extract YAML tags
- Extract main concepts and topics
- Parse current "Related Concepts" section to see existing relationships
2. Extract Key Concepts
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.
- 1mo ago First seen · 731 lines · 11 tokens per session scan A 0b8f03913023
expand-graph is a command published in the GitHub repository witt3rd/claude-plugins (2 stars, last pushed 1y ago), licensed MIT. It adds 11 tokens to every session and 4,608 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.