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.
git clone --depth 1 https://github.com/bluzername/claude-code-power-stackWrote 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/bluzername/claude-code-power-stack/wrapup)<a href="https://agentmods.dev/commands/bluzername/claude-code-power-stack/wrapup"><img src="https://agentmods.dev/badge/commands/bluzername/claude-code-power-stack/wrapup/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.
<a href="https://agentmods.dev/commands/bluzername/claude-code-power-stack/wrapup"><img src="https://agentmods.dev/badge/commands/bluzername/claude-code-power-stack/wrapup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00321 |
| Opus 5.5 | $0.00000 | $0.00128 |
| Sonnet 5.5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
wrapup 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 1mo 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
/wrapup - End-of-session summary and team log
Summarize what was accomplished in this session and offer to log key items for the team.
Steps
1. Summarize the session
Review the current conversation and identify:
- Decisions made
- Things completed
- Unresolved issues or blockers
- Findings worth sharing
2. Update planning files if active
If task_plan.md exists in the current directory:
- Mark completed phases as
complete - Update
progress.mdwith a session summary - Note any new errors or decisions in
task_plan.md
3. Present the wrapup
Wrapup - {today's date}
========================
Done:
- {what was completed}
Decisions:
- {key decisions made and why}
Open:
- {unresolved items, things to pick up next}
Keep it concise - 5-10 lines.
4. Offer to log for the team
If .team/log.jsonl exists (team mode is active), ask:
"Want me to log any of these for the team? I'd suggest:
- [done] {completed item}
- [decision] {key decision}
- [blocker] {if any}"
If the user confirms, run ccs team log for each entry. Then remind them to run ccs team sync to share.
5. Suggest session name
If the session hasn't been named yet, suggest a name using the /rename-session convention so it's findable later.
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.
- 1mo ago First seen · 54 lines · 0 tokens per session scan A f04ece667835
wrapup is a command published in the GitHub repository bluzername/claude-code-power-stack (2 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 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
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
paul:progress
Smart status with routing - suggests ONE next action.
help
Explain Ralph Wiggum technique and available commands.
statusbar
Show current status-bar config and list available styles + themes.
generate-command
Génération Commande Symfony.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.