search-debug

search-debug is a skill for Claude Code, Codex from anortham/julie-plugin. It costs 33 tokens per session (1,168 once invoked), scanned A, a copy of search-debug, MIT.

A debugging guide for Julie, a code-search tool, that investigates why searches return missing, poorly ranked, or irrelevant results.

In plain words
What is it for?
Use it to repeat reported searches, compare lexical, semantic, and hybrid search, check expected symbols, and inspect index health.
Why use it?
It helps separate search-quality problems from symbols that are missing from the index or from differences between search methods.

Skill for Claude CodeCodex

Part of the julie plugin — 6 skills 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/anortham/julie-plugin/search-debug
Any agent
npx skills add anortham/julie-plugin --skill search-debug
Clone the repo
git clone --depth 1 https://github.com/anortham/julie-plugin

Made for: Claude Code, Codex.

Or install julie, the plugin that ships this one along with the rest of its 6 skills.

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 search-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/anortham/julie-plugin/search-debug.svg)](https://agentmods.dev/skills/anortham/julie-plugin/search-debug)
Your own site
<a href="https://agentmods.dev/skills/anortham/julie-plugin/search-debug"><img src="https://agentmods.dev/badge/skills/anortham/julie-plugin/search-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00033 $0.01168
Opus 5 $0.00016 $0.00584
Sonnet 5 $0.00007 $0.00234
Haiku 4.5 $0.00003 $0.00117

Measured 5d ago against content hash 6b75ca072491, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search-debug 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 5d 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.

Origin

This is a copy

100% identical to search-debug — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/search-debug/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Debug

Diagnose why a Julie search returns unexpected results. Use this when a search misses an expected symbol, ranks it too low, or returns irrelevant results. This skill is for Julie dogfooding, not general plugin usage.

Process

Step 1: Reproduce the Search

Run the exact search the user reported:

fast_search(query="<original_query>", limit=20)

fast_search returns mixed-kind results; each hit carries kind. Note what comes back, the top results, their scores, and what's missing. If the default response says "No lexical results. Showing semantic fallback candidates.", treat that as a semantic rescue, not a lexical hit.

If the report involves backend behavior, run the exact requested backend and compare backend="lexical", backend="semantic", and backend="hybrid". Explicit lexical stays pure lexical for bakeoffs; semantic and hybrid are symbol-only concept search.

Step 2: Verify the Expected Symbol Exists

Search for the expected symbol directly:

fast_search(query="<expected_symbol_name>")

If it doesn't appear at all, the symbol may not be indexed.

Step 3: Check Index Health

manage_workspace(operation="health", detailed=true)

Look for:

  • Is the workspace indexed?
  • Are there indexing errors?
  • Is the file containing the expected symbol in the indexed file list?

Step 4: Deep Dive the Expected Symbol

deep_dive(symbol="<expected_symbol>", depth="context")

Check:

  • Centrality: Low-centrality symbols get less boost in search results. Symbols with no references won't benefit from centrality boosting. Use get_context to see the centrality label (low/medium/high).
  • Symbol kind: Is it a function, struct, variable? Variables and constants may score differently.
  • File path: Is it in a test/docs/fixture path? Docs/tests get NL_PATH_PENALTY_DOCS / NL_PATH_PENALTY_TESTS (0.95x); fixture paths get a steeper NL_PATH_PENALTY_FIXTURES (0.75x).
  • Name shape: Does the symbol name break into the tokens the query implies?

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 33 tokens per session scan A 6b75ca072491

Subscribe to this mod's changes

search-debug is a skill published in the GitHub repository anortham/julie-plugin (2 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 1,168 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to search-debug, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens