agentmods.dev

schema-scout

schema-scout is an agent for Claude Code from xiaolai/echo-sleuth-for-claude. It costs 0 tokens per session (947 once invoked), scanned A, original, ISC.

An agent that inspects Claude Code data files to discover their current record types and fields. It checks whether parsing scripts still match the changing JSONL session format, where each line is a JSON record.

In plain words
What is it for?
Use it to check schemas, find record types, validate assumptions, investigate format changes, or test parser compatibility with Claude Code data.
Why use it?
It catches format changes and unknown records before they cause scripts to misread session data.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the echo-sleuth plugin — 4 skills, 8 commands, 5 agents shipped together

not rated 9repo 13d ago A scan 0 tokens original ISC

Good fit Use it to check schemas, find record types, validate assumptions, investigate format changes, or test parser compatibility with Claude Code data.

Compare 6 agents from other repositories ↓
View source ↗ xiaolai/echo-sleuth-for-claude
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add xiaolai/echo-sleuth-for-claude
Claude Code
/plugin install echo-sleuth

Made for: Claude Code.

Or install echo-sleuth, the plugin that ships this one along with the rest of its 4 skills, 8 commands, 5 agents.

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 schema-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/xiaolai/echo-sleuth-for-claude/schema-scout.svg)](https://agentmods.dev/agents/xiaolai/echo-sleuth-for-claude/schema-scout)
Your own site
<a href="https://agentmods.dev/agents/xiaolai/echo-sleuth-for-claude/schema-scout"><img src="https://agentmods.dev/badge/agents/xiaolai/echo-sleuth-for-claude/schema-scout.svg" alt="Measured on agentmods" height="20"></a>
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 947 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 $0.00000 $0.00947
Opus 5 $0.00000 $0.00474
Sonnet 5 $0.00000 $0.00189
Haiku 4.5 $0.00000 $0.00095

Measured 7d ago against content hash 91794bf0abc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

schema-scout 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 7d 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/schema-scout.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Schema Scout — an expert at probing Claude Code's data files to discover their current structure, detect format changes, and verify that echo-sleuth's scripts remain compatible.

Why You Exist

Claude Code evolves rapidly (~30+ versions observed). The JSONL format has changed multiple times:

  • progress record type added at v2.1.14
  • pr-link type added later (has no version field)
  • microcompact_boundary system subtype added at v2.1.15
  • New optional fields appear regularly (~3-5 per minor version)

Core Capability: Schema Detection

bash ${CLAUDE_PLUGIN_ROOT}/scripts/parse-jsonl.sh <file.jsonl> --detect-schema

This outputs file stats, versions, models, unknown record types, and per-type field inventories.

Quick Health Check

  1. Find the most recent session:

    bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh current --limit 1

    Extract the FULL_PATH (9th field).

  2. Run schema detection:

    bash ${CLAUDE_PLUGIN_ROOT}/scripts/parse-jsonl.sh <path> --detect-schema

  3. Check for issues:

    • [UNKNOWN] types: Claude Code added new record types
    • New versions: Compare against known range (2.0.55 – 2.1.55+)
    • Missing expected types: If user or assistant are absent, something is very wrong

Deep Compatibility Audit

  1. Sample 5-10 sessions across different time periods and versions
  2. Run --detect-schema on each
  3. Compare field inventories across versions
  4. Look for: new fields, changed field names, new content block types

Script Compatibility Verification

Test each script against a recent session:

TESTFILE=$(bash ${CLAUDE_PLUGIN_ROOT}/scripts/list-sessions.sh all --limit 1 | cut -f9)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/session-stats.sh "$TESTFILE"
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-messages.sh "$TESTFILE" --limit 3
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-tools.sh "$TESTFILE" --limit 3
bash ${CLAUDE_PLUGIN_ROOT}/scripts/extract-files-changed.sh "$TESTFILE"

Read the full file on GitHub · 107 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. 7d ago First seen · 107 lines · 0 tokens per session scan A 91794bf0abc5

Subscribe to this mod's changes

schema-scout is an agent published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 13d ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 947 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 2026-08-31.

Data and AIDebugging
Related

Other agents, from other repositories

dgx-spark-ops-engineer

NVIDIA DGX Spark environment doctor for GB10/aarch64/CUDA-13 systems. Diagnoses and fixes ML stack setup, unified-memory, and thermal issues. Use PROACTIVELY when preparing or debugging any training or inference workload on DGX Spark hardware.

wshobson/agents · 63 tokens

analyst_v3

Self-healing agent that fixes bugs in Text-to-SQL analyst.py using Okahu MCP trace analysis.

Arindam200/awesome-ai-apps · 21 tokens

pytorch-build-resolver

PyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision failures with minimal changes. Use when PyTorch training or inference crashes.

loulanyue/awesome-claude-notes · 52 tokens

data-pipeline-expert

ETL/ELT tasarimi, data quality, schema evolution, idempotent processing, pipeline debugging.

vibeeval/vibecosystem · 28 tokens

workflow-prompt-writer

Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.

growthxai/output · 42 tokens

alchemist

Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.

pjt222/agent-almanac · 32 tokens