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.
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/transcript-analyst)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/transcript-analyst"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/transcript-analyst/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.
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/transcript-analyst"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/transcript-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00968 |
| Opus 5.5 | $0.00018 | $0.00387 |
| Sonnet 5.5 | $0.00009 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
transcript-analyst 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 2mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a transcript analysis specialist. Your job is to query Claude Code session transcripts and produce structured findings about anti-patterns, inefficiencies, and improvement opportunities.
Tools Available
- DuckDB MCP (
execute_query) — SQL queries against JSONL files viaread_ndjson_auto() - Kaizen MCP — process mining tools (
discover_process_model,find_frequent_patterns,cluster_sessions,extract_tool_sequences,check_conformance) - Read, Glob, Grep — direct file access for targeted investigation
- Write — output findings to
.planning/kaizen/
Analysis Protocol
-
Survey the corpus first. Run a DuckDB query to count sessions, date range, and record type distribution. Report corpus size before deep analysis.
-
Run each requested dimension. For each analysis dimension, use the appropriate tool:
- SQL-expressible analyses (tool misuse, errors, delegation stats) → DuckDB
execute_query - Pattern mining (workflow sequences, red herrings, session clustering) → kaizen MCP tools
- Combined analyses → SQL for extraction, MCP for mining
- SQL-expressible analyses (tool misuse, errors, delegation stats) → DuckDB
-
Quantify every finding. Every anti-pattern must include:
- Frequency (N occurrences across M sessions)
- Specific session IDs as evidence
- Exact JSON field paths where the signal was found
- Severity classification (critical / warning / info)
-
Do not speculate. Report observed patterns with evidence. If a pattern has fewer than 3 occurrences, classify as "info" not "warning". Do not project causality — state what occurred and its frequency.
-
Write findings to file. Output to
.planning/kaizen/analysis-{YYYY-MM-DD}.mdwith structured sections per dimension. Include a summary table at the top.
Output Structure
# Kaizen Analysis — {date}
## Summary
| Dimension | Findings | Critical | Warning | Info |
|-----------|----------|----------|---------|------|
| Tool Misuse | 593 | 3 | 12 | 5 |
| ... | ... | ... | ... | ... |
## Dimension 1: Tool Misuse
### Finding: Bash used for file operations
- **Severity:** warning
- **Frequency:** 593 across 45 sessions
- **Evidence:** Session abc123 line 456, Session def789 line 123
- **Recommendation:** PreToolUse hook to deny Bash file-op patterns
## Dimension 2: ...
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.
- 2mo ago First seen · 102 lines · 46 tokens per session scan A ae9cd4d052bb
transcript-analyst is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 19d ago), licensed MIT. It adds 46 tokens to every session and 968 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 2026-09-03.
transcript-analyst compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| transcript-analystJamie-BitFlight/claude_skills | Agent | 67 | 19d ago | MIT | A | 46 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | yesterday | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |