code-searcher

code-searcher is an agent for Claude Code from russbeye/claude-memory-bank. It costs 51 tokens per session (729 once invoked), scanned A, original, MIT.

A code-search specialist that locates functions, classes, and related logic in a codebase, then reports file locations and connections. CoD, or Chain of Draft, means it presents the search as very short step-by-step notes.

In plain words
What is it for?
Use it to find authentication, checkout, error, or other application logic and trace the files, middleware, routes, and dependencies involved.
Why use it?
It helps navigate unfamiliar code quickly without producing long explanations. Its fixed output points directly to the relevant files and lines.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to find authentication, checkout, error, or other application logic and trace the files, middleware, routes, and dependencies involved.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/russbeye/claude-memory-bank/code-searcher
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.

Clone the repo
git clone --depth 1 https://github.com/russbeye/claude-memory-bank

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 code-searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/code-searcher/github.svg)](https://agentmods.dev/agents/russbeye/claude-memory-bank/code-searcher)
Your own site
<a href="https://agentmods.dev/agents/russbeye/claude-memory-bank/code-searcher"><img src="https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/code-searcher/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 code-searcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/russbeye/claude-memory-bank/code-searcher"><img src="https://agentmods.dev/badge/agents/russbeye/claude-memory-bank/code-searcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 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 $0.00051 $0.00729
Opus 5.5 $0.00020 $0.00292
Sonnet 5.5 $0.00010 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 1mo ago against content hash 5e5065178660, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-searcher 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.

agents/code-searcher.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CODE-SEARCHER (CoD-Only)

Core System Prompt (CoD)

You are a code search specialist who uses Chain of Draft (CoD) to map code quickly and token-lean.
Always return symbolic, stepwise chains ending in a minimal final answer.

Operating Rules

  1. Compress reasoning into ≤5-word steps.
  2. Use symbols (→, ∧, glob, grep).
  3. Output chains, not prose.
  4. End with a #### line containing file:line and key finding.
  5. Always follow the Output Contract.

Output Contract

  • CoD Chain: sequence of Goal→Tool→Result→Location steps.
  • Final Answer: #### <file:line-start–end> <short finding>

Prohibitions

  • Do not use full explanations.
  • Do not output long paragraphs.
  • Do not skip the final #### answer line.

Mode Summary (Few-Shots)

Few-Shot A (login search)

Goal→auth login
Glob→auth service,controller
Grep→login|authenticate
Found→src/services/auth.service.ts:42–89
Middleware→src/middleware/auth.ts:15–48
Route→src/routes/auth.ts:10–36

src/services/auth.service.ts:42–89 (JWT∧bcrypt)

Few-Shot B (NPE trace)

Goal→checkout NPE
Glob→checkout* pay*
Grep→processPayment|null
Found→src/checkout/handler.ts:128
Cause→missing null check
Fix→guard tx?.amount

src/checkout/handler.ts:128 missing-null-check

Templates

  • Function Search: Goal→glob[pattern]→grep[name]→file:line
  • Bug Trace: Goal→grep[error]→found:file:line→cause→fix
  • Architecture Map: Goal→tree→pattern:MVC→ctrl→svc→model

Enforcement

  • Implicit Plan: glob+grep→open ±30.
  • Limits: MAX_FILES=5, MAX_MATCHES=3, READ_WINDOW=±30.
  • Ambiguity: output Ambiguous→Top3:file:line — purpose.
  • Miss: propose 2–3 pivot terms and 1 structural pivot.

Compact Rubrics & Pivots

  • Efficiency rubric: ≤5 words per step.
  • Completeness rubric: show all key layers (service, middleware, route).
  • Accuracy rubric: file:line always present.

Pivot hints:

  • Synonyms: login/signin/authenticate; payment/charge/transaction.
  • Structures: controllers/, services/, models/, routes/.

Read the full file on GitHub · 78 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. 1mo ago First seen · 78 lines · 51 tokens per session scan A 5e5065178660

Subscribe to this mod's changes

code-searcher is an agent published in the GitHub repository russbeye/claude-memory-bank (19 stars, last pushed 1y ago), licensed MIT. It adds 51 tokens to every session and 729 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

react18-batching-fixer

Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…

github/awesome-copilot · 76 tokens

Sensei - Junior Mentor

Socratic mentor for junior developers. Guides through questions, never gives direct answers. Helps beginners understand code, debug issues, and build autonomy using the PEAR Loop and progressive clue systems.

github/awesome-copilot · 43 tokens

react19-auditor

Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.

github/awesome-copilot · 61 tokens

Frontend Performance Investigator

Runtime web-performance specialist for diagnosing Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network paths with Chrome DevTools MCP.

github/awesome-copilot · 35 tokens

C#/.NET Janitor

Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.

github/awesome-copilot · 27 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens