agentmods.dev

claude-code-interactive-mode: Command for Claude Code

.claude/commands/pr-start.md

pr-start is a command for Claude Code from inadarei/claude-code-interactive-mode. It costs 0 tokens per session (399 once invoked), scanned A, original, MIT.

A command that begins a record of the coding conversation for a pull request, which is a proposed code change for review. It stores the ticket number, start time, and conversation transcript path in a tracking file.

In plain words
What is it for?
Use it when starting work tied to a ticket so the session can be tracked in pr-chats/.pr-tracking.json.
Why use it?
It makes it easier to connect later discussion and captured work to the correct ticket. It also records the actual start time instead of relying on an estimate.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is inadarei/claude-code-interactive-mode's own configuration. It tells Claude Code how to work on claude-code-interactive-mode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-interactive-mode configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/.claude/projects/-Users-me-myproject/abc123.jsonl.

not rated 11repo 6mo ago A scan 0 tokens original MIT
View source ↗ inadarei/claude-code-interactive-mode
Reuse

Borrowing it

Nothing to install: this file belongs to inadarei/claude-code-interactive-mode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inadarei/claude-code-interactive-mode/main/.claude/commands/pr-start.md
Clone the repo
git clone --depth 1 https://github.com/inadarei/claude-code-interactive-mode

Made for: Claude Code.

Wrote 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.

agentmods badge for pr-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/inadarei/claude-code-interactive-mode/pr-start/github.svg)](https://agentmods.dev/commands/inadarei/claude-code-interactive-mode/pr-start)
Your own site
<a href="https://agentmods.dev/commands/inadarei/claude-code-interactive-mode/pr-start"><img src="https://agentmods.dev/badge/commands/inadarei/claude-code-interactive-mode/pr-start/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.

agentmods 80×15 button for pr-start

Your own site · 80×15
<a href="https://agentmods.dev/commands/inadarei/claude-code-interactive-mode/pr-start"><img src="https://agentmods.dev/badge/commands/inadarei/claude-code-interactive-mode/pr-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00399
Opus 5.5 $0.00000 $0.00160
Sonnet 5.5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2mo ago against content hash 1252020abca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-start 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.

.claude/commands/pr-start.md · 21 lines

What it actually says

Start tracking a PR chat log for ticket: $ARGUMENTS

Follow these steps to start tracking a PR chat log for the specified ticket:

  1. Read the current tracking file at pr-chats/.pr-tracking.json if it exists, otherwise start with an empty JSON object {}.

  2. CRITICAL: run date -u +"%Y-%m-%dT%H:%M:%SZ" in the shell and use the output as the current UTC timestamp. Do NOT guess or estimate the time — you must use the actual command output.

  3. Find the current session's JSONL transcript file. Run this shell command to get the path:

    PROJECT_DIR="$(pwd)"; ENCODED="${PROJECT_DIR//\//-}"; ls -1t "$HOME/.claude/projects/$ENCODED"/*.jsonl 2>/dev/null | head -1

    Use the output as the session file path. If the command returns nothing, warn me but continue (the capture script will fall back to searching at capture time).

  4. Add an entry to the JSON object with the ticket ID "$ARGUMENTS" as the key, and an object value containing:

    • "start_ts": the UTC timestamp from step 2
    • "session_file": the JSONL file path from step 3 (or null if not found)

    Example: {"test-ticket-123": {"start_ts": "2026-03-26T21:08:21Z", "session_file": "/Users/me/.claude/projects/-Users-me-myproject/abc123.jsonl"}}

  5. Write the updated JSON to pr-chats/.pr-tracking.json.

  6. Confirm to me that PR chat tracking has started for ticket "$ARGUMENTS" at the recorded timestamp.

Important: if "$ARGUMENTS" is empty, ask me to provide a ticket ID.

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. 2mo ago First seen · 21 lines · 0 tokens per session scan A 1252020abca0

Subscribe to this mod's changes

pr-start is a command published in the GitHub repository inadarei/claude-code-interactive-mode (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 399 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.

Git and workflow
Related

pr-start compared with commands from other repositories

pr-start next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pr-startinadarei/claude-code-interactive-modeCommand116mo agoMITA0Claude Code
merge-conflict-analysisrjmurillo/ai-agentsCommand49yesterdayMITA0GitHub Copilot
release-notesOpenHands/extensionsCommand176yesterdayMITA44Claude Code
commitechoVic/blade-codeCommand18124d agoMITA8Claude Code
repo-audittractorjuice/arc-kitCommand2.3k2d agononeA29Claude Code
propsmill/infrahub-mcpCommand10yesterdayApache-2.0A18Claude Code
codex-reviewoalders/kitchen-sinkCommand54d agoMITA41Claude Code