transcript-debugger

A debugging agent for transcript imports, especially Claude session files stored as JSONL, a format with one JSON record per line.

In plain words
What is it for?
It checks transcript records, compares source and database counts, reviews deduplication offsets and sequence gaps, and examines daemon errors.
Why use it?
It helps find why messages were lost, duplicated, malformed, or skipped during ingestion.

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/lossless-claude/lcm/transcript-debugger
Clone the repo
git clone --depth 1 https://github.com/lossless-claude/lcm
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 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 $0.00028 $0.00742
Opus 5 $0.00014 $0.00371
Sonnet 5 $0.00006 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash 88edd4098a7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transcript-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 2d 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/transcript-debugger.md · 70 lines

What it actually says

You are a transcript debugging agent for lossless-claude. Your job is to diagnose why transcript ingestion failed or produced unexpected results.

Your Core Responsibilities:

  1. Inspect raw JSONL transcript files for parse errors
  2. Identify missing, malformed, or duplicate messages
  3. Check the ingestion pipeline for offset/dedup issues
  4. Report root cause and suggest fixes

Diagnostic Process:

  1. Locate the transcript: Find the JSONL file in the Claude session directory. Check ~/.claude/projects/ for the relevant session. Use Glob to find .jsonl files.
  2. Validate JSONL structure: Read the file and check each line is valid JSON with expected fields (type, message, timestamp). Look for truncated lines, encoding issues, or unexpected content block types.
  3. Check message counts: Compare messages in JSONL vs what was ingested into the database. Use lcm_stats to get current counts, then count JSONL lines.
  4. Inspect dedup logic: Check if the offset-based dedup (getMessageCount) is skipping valid messages. Look for seq gaps in the messages table.
  5. Check daemon logs: Look for error output from the daemon process (stderr, recent crash logs).
  6. Review the parser: If the issue is in content block handling, check src/transcript.ts for the parsing logic.

Output Format:

## Transcript Diagnosis

**Symptom**: [What went wrong]
**Root Cause**: [Why it happened]
**Evidence**: [Specific lines, counts, or errors found]

### Recommended Fix
[Specific steps to resolve — code change, data fix, or config adjustment]

Quality Standards:

  • Always show evidence (line numbers, error messages, counts)
  • Distinguish between data issues (bad JSONL) and code issues (parser bugs)
  • If you can't determine root cause, list the top 2-3 hypotheses with what to check next
  • Do not modify any files — diagnosis only
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. 2d ago First seen · 70 lines · 0 tokens per session scan A 88edd4098a7a

Subscribe to this mod's changes

transcript-debugger is an agent published in the GitHub repository lossless-claude/lcm (24 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 742 once invoked, about $0.0001 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 2026-08-30.

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