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/ustoppble/overclickWrote 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/ustoppble/overclick/deliver)<a href="https://agentmods.dev/commands/ustoppble/overclick/deliver"><img src="https://agentmods.dev/badge/commands/ustoppble/overclick/deliver/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/ustoppble/overclick/deliver"><img src="https://agentmods.dev/badge/commands/ustoppble/overclick/deliver.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 | $0.00014 | $0.00193 |
| Opus 5.5 | $0.00006 | $0.00077 |
| Sonnet 5.5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
deliver 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 27d 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
Load the bundled overclick skill and read its linked canonical OVERCLICK.md.
Find this session's single executing card with task_list
using status: "em_execucao", claimed_by: "me", and the session_id declared
in this session's claim; stop if the session is unknown, or there is none or
more than one. Run its binary confirmation checks, commit with the card prefix,
and push the registered branch. Cite the full Git commit ID in evidence. Call
task_deliver with a truthful summary, check results, branch, verification
entry point and transcript. On Claude Code omit usage: the plugin's hook
measures it from this session's transcript. Elsewhere run the exact usage
recipe from the claim briefing and send the measured usage. Never mark the card
validated.
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.
- 27d ago Changed · +2 lines 9f5168115876
- 1mo ago Changed · +1 lines f13a594ae52e
- 1mo ago First seen · 13 lines · 14 tokens per session scan A 28d6cbeed02d
deliver is a command published in the GitHub repository ustoppble/overclick (119 stars, last pushed 26d ago), licensed MIT. It adds 14 tokens to every session and 193 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
auto-sprint
Orchestrateur de sprint de bout en bout (démarrage -> décomposition -> validation -> implémentation -> PR -> CI -> revue -> rétro -> merge).
flux-status
Show current Flux board status and what to work on next.
start-development
Start development workflow process in Moira.
quick-push
Git add all, commit with Claude, and push to current/new feature branch.
review
Préparation Sprint Review.