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 commands/inadarei/claude-code-interactive-mode/pr-chat-capture-readmegit clone --depth 1 https://github.com/inadarei/claude-code-interactive-modeWrote 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/inadarei/claude-code-interactive-mode/pr-chat-capture-readme)<a href="https://agentmods.dev/commands/inadarei/claude-code-interactive-mode/pr-chat-capture-readme"><img src="https://agentmods.dev/badge/commands/inadarei/claude-code-interactive-mode/pr-chat-capture-readme.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 | $0.00000 | $0.00585 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
PR-CHAT-CAPTURE-README 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Chat Log Capture
Capture Claude Code conversation logs and attach them to pull requests.
Setup
Ensure the following files are in your project:
.claude/
commands/
pr-start.md # /pr-start slash command
pr-end.md # /pr-end slash command
scripts/
pr-capture.sh # extraction + formatting script
pr-chats/
.gitkeep # output directory
Dependency: python3 must be available (no pip packages needed).
Usage
1. Start tracking
When you begin work on a ticket, run in Claude Code:
/pr-start TICKET-123
This records the current timestamp. Everything from this point forward will be captured.
2. Work normally
Have your conversation with Claude Code as usual — coding, debugging, discussing architecture, whatever.
3. End tracking and capture
When you're ready to create the PR:
/pr-end TICKET-123
This extracts the conversation from the start marker to now and produces three Markdown files:
pr-chats/YY-MM-DD-HH-MM-TICKET-123-detailed.md
pr-chats/YY-MM-DD-HH-MM-TICKET-123-brief.md
pr-chats/YY-MM-DD-HH-MM-TICKET-123-summary.md
4. Commit with your PR
git add pr-chats/
git commit -m "Add Claude chat log for TICKET-123"
Output Format
Three versions are produced:
- Detailed — Full conversation with user messages (👤), assistant responses (🤖), and summarized tool calls (🔧: file paths for reads/writes/edits, commands for bash, queries for web search). Full tool output is omitted for readability.
- Brief — Same as detailed but with all tool call sections removed.
- Summary — An LLM-generated summary of the conversation: a short paragraph describing what was discussed, followed by a bullet list of key decisions made and actions taken.
Slash commands (/pr-start, /pr-end, etc.) are automatically collapsed to
their short form — the expanded command template is not included in the output.
Notes
- Tracking state is stored in
pr-chats/.pr-tracking.json(add to.gitignoreif you prefer) - You can track multiple tickets simultaneously
- The script uses the most recently modified
.jsonlsession file — if you--resumemid-tracking, ensure you're in the same session - The
pr-chats/directory can be added to.gitignoreif you prefer linking logs externally rather than committing them
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.
- 6d ago First seen · 89 lines · 0 tokens per session scan A f00d91e8c67f
PR-CHAT-CAPTURE-README is a command published in the GitHub repository inadarei/claude-code-interactive-mode (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 585 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 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.