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-endgit clone --depth 1 https://github.com/inadarei/claude-code-interactive-modeWhat 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 | $0.00000 | $0.00579 |
| Opus 5 | $0.00000 | $0.00290 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
pr-end 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 3d 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.
What it actually says
End PR chat tracking for ticket: $ARGUMENTS
Follow these steps to end PR chat tracking for the specified ticket:
-
Read
pr-chats/.pr-tracking.json. If it doesn't exist or doesn't contain ticket "$ARGUMENTS", tell me and stop. -
Get the start timestamp for ticket "$ARGUMENTS". If it doesn't exist, tell me and stop.
-
Run the capture script to produce the detailed version:
bash ~/.claude/scripts/pr-capture.sh "$ARGUMENTS"If the script doesn't exist, or is not executable, or fails in any other way - provide appropriate error message and abort the rest of the process. DO NOT try to recover, since it can damage the source files and destroy data.
The script will find the current session's JSONL transcript, extract all entries from the start timestamp to now, format them as readable Markdown (human messages, assistant responses, and summarized tool calls), and save to
pr-chats/YY-MM-DD-HH-MM-<ticket-id>-detailed.md.Validation: After the script runs, check its output for the number of messages captured. If it reports 0 messages or the detailed file is empty/missing, STOP and report the error to the user. Do NOT proceed to create full or summary files — the capture failed and needs debugging. Common causes: the start timestamp in
.pr-tracking.jsonis in the future (was it recorded correctly viadate -u?), or the session JSONL file wasn't found. -
Read the detailed file the script produced. Using it as source, create two additional files:
- Full version (
pr-chats/YY-MM-DD-HH-MM-<ticket-id>-brief.md): A mechanical filter of the detailed file — copy it verbatim but remove all tool call sections (lines starting with### 🔧 Tool:through to the next##heading or end of file). Do NOT rephrase, summarize, or rewrite any content. The brief must contain the exact same human and assistant text as the detailed file. - Summary version (
pr-chats/YY-MM-DD-HH-MM-<ticket-id>-summary.md): A concise, LLM-generated summary containing:- A short paragraph summarizing the conversation (what was discussed, what was the goal)
- A bullet list of key decisions made and actions taken (files created/modified, architectural choices, etc.)
- Full version (
-
Remove the "$ARGUMENTS" entry from
pr-chats/.pr-tracking.json. -
Tell me the output file paths and a brief summary (number of messages captured).
Important: if "$ARGUMENTS" is empty, ask me to provide a ticket ID.
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.
- 3d ago First seen · 25 lines · 0 tokens per session scan A 37825b6a410d
pr-end 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 579 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.