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/eddiesanjuan/markupr/pick-taskgit clone --depth 1 https://github.com/eddiesanjuan/markuprWrote 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/eddiesanjuan/markupr/pick-task)<a href="https://agentmods.dev/commands/eddiesanjuan/markupr/pick-task"><img src="https://agentmods.dev/badge/commands/eddiesanjuan/markupr/pick-task.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 | $0.00000 | $0.00316 |
| Opus 5 | $0.00000 | $0.00158 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
pick-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are an ORCHESTRATOR picking up a queued task from GitHub.
- Run:
gh issue list --repo eddiesanjuan/$REPO_NAME --label agent-task --label ready --state open --json number,title,body --limit 1 - If no issues found, say "No tasks queued for this repo" and stop.
- Take the first issue. Comment on it: "🤖 Picked up by Claude Code on Eddie's laptop."
- Relabel:
gh issue edit <number> --add-label in-progress --remove-label ready - Read the issue body — it contains your full task instructions.
- Execute the task. Follow the instructions precisely.
- When done:
- Commit your work to a new branch (never main)
- Push the branch
- Create a PR with a clear description of what changed
- Comment on the issue with a link to the PR
- Relabel:
gh issue edit <number> --add-label completed --remove-label in-progress
- If you fail or hit a blocker:
- Comment on the issue explaining what went wrong
- Relabel:
gh issue edit <number> --add-label failed --remove-label in-progress
CRITICAL RULES:
- Never push to main
- Always create a PR
- If the task says "be cautious" or "preserve good state" — run tests before committing
- One task at a time. Run this command again for the next one.
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.
- 4d ago First seen · 24 lines · 0 tokens per session scan A a4a519fcfe70
pick-task is a command published in the GitHub repository eddiesanjuan/markupr (18 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 316 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
backlog-from-demo
Turn a recorded product demo into a prioritized backlog with timestamped evidence.
process
Process one or more YouTube videos (or a playlist) into structured knowledge.
kg_navigator
Knowledge graph specialist for entity relationships across videos.
video_specialist
Deep-dive analyst for processed video content. Use to answer specific questions about what was said, strategies mentioned, or claims made in a video.
voxpip
Watch any video and get a transcript — even without an API key. Extends /watch with a local speech-to-text fallback.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.