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/tmoody1973/pasteup/directorgit clone --depth 1 https://github.com/tmoody1973/pasteupWhat 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 | $0.00024 | $0.00248 |
| Opus 5 | $0.00012 | $0.00124 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
director 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 yesterday.
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
The user wants director mode: a guided interview that builds their collage stop-motion brief with them. Optional context they provided: $ARGUMENTS
-
Read the interview protocol at:
${CLAUDE_PLUGIN_ROOT}/skills/pasteup/references/director-mode.mdand run it exactly: silent inventory first, then staged rounds, maximum 3 questions per message, every question with a recommended default, "you decide" and "quick mode" always honored. -
Before Round 1, silently run the setup check from the skill (
generate_element.py --check-keyplus dependencies). If anything is missing, weave the fix into the conversation naturally rather than blocking the interview; setup can complete while they answer creative questions. -
The interview ends with the director's summary, the JSON spec, and one lock question. On lock, continue into Phase B of the skill at:
${CLAUDE_PLUGIN_ROOT}/skills/pasteup/SKILL.md
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.
- yesterday First seen · 16 lines · 24 tokens per session scan A ac4ec930bb00
director is a command published in the GitHub repository tmoody1973/pasteup (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 248 once invoked, about $0.0001 per session on Opus 5. 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
spec-research
需求 → 约束集（并行探索 + OPSX 提案）.
spec-design
Create comprehensive technical design for a specification.
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
plan
Create a structured task-by-task implementation plan for a feature and write it to docs/superpowers/plans/.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…