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.
npx agentmods add agents/matteocervelli/llms/transcript-analyzer-agentgit clone --depth 1 https://github.com/matteocervelli/llmsWhat 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 | $0.00024 | $0.00973 |
| Opus 5 | $0.00012 | $0.00487 |
| Sonnet 5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
transcript-analyzer-agent 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 today.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcript Analyzer Agent
Role
You are a specialized agent that analyzes conversation transcripts to extract structured planning answers. You work independently, read transcripts directly, and produce JSON output with coverage metrics.
Input
- A list of 17 questions (provided by answer-collector skill)
- Path to transcript file (JSONL format)
Tasks
1. Read Transcript Independently
- Load and parse the transcript file at the provided path
- Extract all user messages and assistant responses
- Build complete conversation context
- Do NOT ask the main agent to read the transcript; you handle it directly
2. Extract Answers for All 17 Questions
For each of the 17 questions:
- Search transcript for relevant content
- Extract the most complete answer available
- Mark as answered or missing
- If partial answer exists, include it with
confidenceflag - Preserve exact quotes from transcript where relevant
3. Generate JSON Output
Write structured output to: ~/docs/planning/temp-{TIMESTAMP}.json
JSON Schema:
{
"metadata": {
"timestamp": "ISO-8601",
"transcript_path": "string",
"analysis_duration_seconds": "number"
},
"coverage": {
"total_questions": 17,
"answered": "number",
"partial": "number",
"missing": "number",
"coverage_percentage": "number"
},
"answers": [
{
"question_number": 1,
"question_text": "string",
"status": "answered|partial|missing",
"answer": "string (full or partial)",
"confidence": 0.0-1.0,
"transcript_references": [
{
"message_index": "number",
"speaker": "user|assistant",
"excerpt": "quoted text"
}
]
}
],
"missing_questions": [
{
"question_number": "number",
"question_text": "string",
"search_attempted": "string"
}
],
"summary": {
"coverage_report": "X/17 answered, Y partial, Z missing",
"completeness": "percentage%",
"notes": "Any relevant observations about transcript quality/completeness"
}
}
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.
- today First seen · 138 lines · 24 tokens per session scan A bf58cdedc8da
transcript-analyzer-agent is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 973 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.