refs

A command that finds every use of a named code element across the project, using a language server or text search as a fallback.

In plain words
What is it for?
Use it to find call sites and other references, with each result showing its file, line, and a short context line.
Why use it?
It shows where a function, class, or other symbol is used without requiring you to inspect files one by one.

Command

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 commands/benmarte/codemunch/refs
Clone the repo
git clone --depth 1 https://github.com/benmarte/codemunch
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 168 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 $0.00016 $0.00168
Opus 5 $0.00008 $0.00084
Sonnet 5 $0.00003 $0.00034
Haiku 4.5 $0.00002 $0.00017

Measured yesterday against content hash 16274ffe57f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refs 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 yesterday.

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.

commands/refs.md · 17 lines

What it actually says

First, run the staleness-gate skill to ensure the index is fresh.

Then run the LSP skill's "Find all references" operation for: $ARGUMENTS

  1. Look up the symbol in the codemunch index to get its file and line
  2. Use LSP textDocument/references at that position (if LSP configured)
  3. OR use ripgrep fallback if no LSP available
  4. Return compact list of references with file, line, and one line of context
  5. Report token savings vs reading all reference files

End with: "Use /codemunch:fetch to read any of these call sites."

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. yesterday First seen · 17 lines · 16 tokens per session scan A 16274ffe57f9

Subscribe to this mod's changes

refs is a command published in the GitHub repository benmarte/codemunch (7 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 168 once invoked, about $0.0001 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.