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/davistroy/claude-marketplaceWrote 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/commands/davistroy/claude-marketplace/analyze-transcript)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/analyze-transcript"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/analyze-transcript.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 | $0.00006 | $0.03241 |
| Opus 5 | $0.00003 | $0.01621 |
| Sonnet 5 | $0.00001 | $0.00648 |
| Haiku 4.5 | $0.00001 | $0.00324 |
Grade A, and why
analyze-transcript 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.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Transcript Analysis
Analyze a meeting transcript and produce a comprehensive markdown report with key discussion points, action items, decisions, and risks.
Input Validation
Required Arguments:
<transcript-path>- Path to the transcript file
Optional Arguments:
--format [md|json|interview-record]- Output format (default: md)md: Markdown report with sections and tables (default)json: Structured data with sections, action_items, decisions arraysinterview-record: Dated markdown record with YAML frontmatter, suited to a knowledge repo's immutable sources directory (see Interview-Record Format)
--preview- Show summary and ask for confirmation before saving (see common-patterns.md)--no-prompt- Skip confirmation prompts. Use defaults for all options.
Validation: If no transcript is provided:
- If
--no-promptis specified, display the error and exit:
Error: Missing required argument
Usage: /analyze-transcript <transcript-path> [--format md|json|interview-record] [--preview] [--no-prompt]
Example: /analyze-transcript meeting-notes.txt
Example: /analyze-transcript transcript.md --format json
- Otherwise (default), prompt interactively using the input flow below.
Input Flow
Follow this concrete sequence to obtain the transcript:
Step 1: Determine input source
If a file path was provided as an argument, proceed to Step 2. Otherwise, ask:
How would you like to provide the transcript?
1. File path — Provide the path to a transcript file (e.g., meeting-notes.txt)
2. Paste — Paste the transcript content directly into the chat
Enter choice (1 or 2):
Step 2: Acquire the transcript
- If file path: Read the file using the Read tool. Validate the file (see Error Handling section).
- If paste: Accept the pasted content. The user may need multiple messages for long transcripts. Ask "Is that the complete transcript, or is there more?" after the first paste.
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.
- 7d ago First seen · 373 lines · 6 tokens per session scan A 941805d0f30c
analyze-transcript is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 7d ago), licensed MIT. It adds 6 tokens to every session and 3,241 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.