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/paulbreuler/limps/pr-commentsgit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.01270 |
| Opus 5 | $0.00000 | $0.00635 |
| Sonnet 5 | $0.00000 | $0.00254 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
pr-comments 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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Comments
Fetch, review, address, and resolve unresolved PR review comments using the scripts/helpers/pr-comments.ts helper.
Instructions for Claude
When this command is invoked:
- List unresolved threads: Use
npx tsx scripts/helpers/pr-comments.ts list [pr_number]- Shows thread IDs, file paths, comments, and comment IDs
- Optionally specify PR number, or omit to use current branch's PR
- Analyze by file: Use
npx tsx scripts/helpers/pr-comments.ts analyze [pr_number]- Groups threads by file path
- Shows which files exist vs. deleted
- Helps prioritize which comments to address
- Address comments:
- Before fixing: For architecture/maintainability concerns, run
/branch-code-reviewto understand impact - Before fixing: For security/MCP concerns, run
/mcp-code-reviewto identify risks - After fixing: If fixes were made, commit using conventional commits (use
/git-commit-best-practices) - Commit message: Reference the comment/concern:
fix(component): address review feedback on error handling
- Before fixing: For architecture/maintainability concerns, run
- Reply to comments: Use
npx tsx scripts/helpers/pr-comments.ts reply [pr_number] <comment_id> <message>- See reply templates below for common responses
- Resolve threads: Use
npx tsx scripts/helpers/pr-comments.ts resolve <thread_id>- Only after addressing and committing fixes (or explaining why no fix needed)
Quick Start
# List all unresolved threads on current PR
npx tsx scripts/helpers/pr-comments.ts list
# Analyze threads by file
npx tsx scripts/helpers/pr-comments.ts analyze
# Reply to a specific comment
npx tsx scripts/helpers/pr-comments.ts reply [pr_number] <comment_id> "Your reply message here"
# Resolve a thread after addressing
npx tsx scripts/helpers/pr-comments.ts resolve <thread_id>
Helper Script Commands
list [pr_number]
Lists all unresolved review threads with their comments.
npx tsx scripts/helpers/pr-comments.ts list
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.
- 2d ago First seen · 173 lines · 0 tokens per session scan A f0fc3b752b83
pr-comments is a command published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,270 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 2026-08-31.
Other commands, from other repositories
plan-new
Create a new plan using the Universal Planning Framework.
plan-review
Check plan quality against Universal Planning Framework standards.
interview-plan
Interview a plan using framework-aware questions across 3 depth tiers.
plan-refine
Autonomously stress-test and harden a plan through 6 adversarial perspectives.
start
Enter Fathom Mode with a task. Bare /fathom:start shows status only via hook (no LLM).
plan
Plan from the current Fathom session, grounded in a structured intent.