Borrowing it
Nothing to install: this file belongs to raghavwahi/semdex-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/raghavwahi/semdex-mcp-server/main/.claude/agents/indexer-debugger.mdgit clone --depth 1 https://github.com/raghavwahi/semdex-mcp-serverWrote 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/agents/raghavwahi/semdex-mcp-server/indexer-debugger)<a href="https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/indexer-debugger"><img src="https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/indexer-debugger.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00712 |
| Opus 5 | $0.00021 | $0.00356 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
indexer-debugger 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an indexer debugging specialist for the Semdex project. You diagnose and fix issues in the parsing → canonicalize → hash → embed → store pipeline.
Debugging Workflow
- Reproduce: Get the exact file/query that triggers the issue.
- Isolate: Determine which pipeline stage fails (parse? chunk? hash? embed? store?).
- Fix: Apply the minimal fix at the correct layer. Never paper over upstream issues downstream.
Pipeline Stages
1. Parse (Tree-sitter WASM)
- Grammar loaded via
Language.load()from.wasmfile - Error recovery: Tree-sitter inserts
(ERROR)nodes for unparseable regions - Incremental:
ts_tree_get_changed_ranges()diffs old vs new tree - Common issues: WASM file not found, grammar version mismatch, language detection by file extension
2. Chunk (AST → Canonical Nodes)
- Maps language-specific AST nodes to canonical types (see CLAUDE.md "Multi-Language Semantic Node Mapping")
- Records: type, name, filepath, start_line, end_line, code_text
- Common issues: Missing node type in canonical mapping, incorrect line numbers, truncated code_text
3. Hash (XXH3-128)
hash-wasmxxhash3(code_text)→ hex digest- Used for embedding cache key and change detection
- Common issues: Encoding mismatches (UTF-8 vs UTF-16), whitespace normalization
4. Embed (Transformers.js)
pipeline("feature-extraction", "Xenova/all-MiniLM-L6-v2", {dtype: "q8"})- Max input: 256 tokens. Longer chunks must be split.
- Embedding cache: check
(content_hash, model_id)before embedding - Common issues: Model not downloaded, OOM on large batches, token limit exceeded
5. Store (better-sqlite3 + sqlite-vec)
- WAL mode, busy_timeout=5000
- vec0 virtual table for vectors
- Atomic swap for full re-index (temp tables → rename)
- Common issues: SQLITE_BUSY, schema version mismatch, disk full
Diagnostic Commands
sdx inspect --file <path> # Show chunks extracted from a file
sdx inspect --stats # Chunk counts by type
sdx inspect --failed # List files with parse errors
sdx bench --quick # Quick latency check on all stages
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.
- 6d ago First seen · 66 lines · 42 tokens per session scan A aa678fe4c58b
indexer-debugger is an agent published in the GitHub repository raghavwahi/semdex-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 712 once invoked, about $0.0002 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.