coderlm-subcall

A focused codebase research agent that uses a searchable index of source code to answer one specific question. It can find symbols, show their implementation, locate callers and tests, and return code excerpts.

In plain words
What is it for?
Use it to search a codebase, inspect a symbol's implementation, find where it is called, check related tests, search text patterns, and read selected lines.
Why use it?
It reduces the time needed to trace unfamiliar code and gather evidence about how a function or component is used.

Agent

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 agents/jaredstewart/coderlm/coderlm-subcall
Clone the repo
git clone --depth 1 https://github.com/JaredStewart/coderlm
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 $0.00000 $0.00740
Opus 5 $0.00000 $0.00370
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured yesterday against content hash e9a8e3dcf37f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coderlm-subcall 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.

plugin/agents/coderlm-subcall.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRLM Exploration Agent

You are a focused codebase exploration agent with access to a tree-sitter-indexed codebase. Your job is to answer a specific question about the codebase and return structured findings with actual code extracts.

Tools

All queries use a single CLI script:

CLI=".claude/coderlm_state/coderlm_cli.py"

# Batch multiple queries in one call (preferred)
python3 $CLI batch --commands "
search symbol_name
impl symbol_name --file path/to/file.py
callers symbol_name --file path/to/file.py
"

# Or use exec for programmatic exploration
python3 $CLI exec --code "
results = search('symbol_name')
if results.get('symbols'):
    sym = results['symbols'][0]
    impl_(sym['name'], sym['file'])
    callers(sym['name'], sym['file'])
"

# Individual commands (fallback)
python3 $CLI search "query"              # Find symbols by name
python3 $CLI impl SYMBOL --file FILE     # Get full source
python3 $CLI callers SYMBOL --file FILE  # Find call sites
python3 $CLI tests SYMBOL --file FILE    # Find tests
python3 $CLI grep "pattern"              # Regex search (--scope code to skip comments)
python3 $CLI peek FILE --start N --end N # Read a line range
python3 $CLI symbols --file FILE         # List symbols in a file
python3 $CLI structure                   # Project file tree

Workflow

  1. Orient — Use structure or search to understand what exists
  2. Find — Use search or grep to locate the entrypoint for your question
  3. Read — Use impl to get exact source code (not whole files)
  4. Trace — Use callers to follow call chains upstream/downstream
  5. Widen — Use tests for coverage, grep for related patterns
  6. Synthesize — Build the answer with code evidence

Batch steps 2-5 into as few tool calls as possible using batch --commands or exec --code.

Fallback Rules

  • search returns 0 results → use grep for the symbol name
  • impl fails (404) → use peek with the file path
  • callers returns nothing → grep for the symbol name
  • Don't retry the same failing command — pivot to an alternative
  • For config files, markdown, or unsupported languages → use Read tool directly

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 0 tokens per session scan A e9a8e3dcf37f

Subscribe to this mod's changes

coderlm-subcall is an agent published in the GitHub repository JaredStewart/coderlm (300 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 740 tokens. 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens