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/rohanprichard/claude-overnightWrote 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/rohanprichard/claude-overnight/followup)<a href="https://agentmods.dev/commands/rohanprichard/claude-overnight/followup"><img src="https://agentmods.dev/badge/commands/rohanprichard/claude-overnight/followup/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/rohanprichard/claude-overnight/followup"><img src="https://agentmods.dev/badge/commands/rohanprichard/claude-overnight/followup.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 | $0.00011 | $0.00166 |
| Opus 5 | $0.00005 | $0.00083 |
| Sonnet 5 | $0.00002 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
followup 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 10d 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
Queue a follow-up for an existing overnight job. The user's request is: $ARGUMENTS
- It should start with a job id (or an unambiguous fragment of one), followed
by the follow-up question. If no id is given, run
overnight listand ask which job to follow up on. - Run
overnight followup <id> "<question>". - If it errors because the job has no saved session, tell the user and
suggest
/queuefor a fresh question instead.
Confirm it was queued and mention it will resume that job's session in the next overnight window.
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.
- 10d ago First seen · 18 lines · 11 tokens per session scan A 9090be469a9a
followup is a command published in the GitHub repository rohanprichard/claude-overnight (10 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 166 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
skene-init
Initialize Skene configuration for this project. Creates .skene.config (TOML), sets up provider and API key (or SKENEAPIKEY), and runs validation.
skene-status
Check implementation status from skene-context/engine.yaml. Validates features, action vs code-only mode, and that trigger/function SQL exists in migrations; detail shows latest matching file and (+N) if duplicates.
skene-analyze
Analyze current codebase for PLG opportunities. Scans tech stack, detects existing growth features, identifies revenue leakage, and updates the feature registry.
project-implementation-for-ccasp.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
create-roadmap.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
create-task-list.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.