execute-at-reset

A command that schedules a saved plan to run shortly after the five-hour usage window resets.

In plain words
What is it for?
Use it to schedule a one-time task from an absolute plan-file path after the next five-hour rate-limit reset.
Why use it?
It lets the agent defer execution when the current usage limit does not leave enough room, provided the reset time and plan file meet the command’s requirements.

Command

Install

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.

agentmods
npx agentmods add commands/rhan1/crewline/execute-at-reset
Clone the repo
git clone --depth 1 https://github.com/rhan1/crewline
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00569
Opus 5 $0.00006 $0.00284
Sonnet 5 $0.00003 $0.00114
Haiku 4.5 $0.00001 $0.00057

Measured 2d ago against content hash 74b05cad26b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-at-reset 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 2d 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.

commands/execute-at-reset.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schedule a one-shot execution that fires ~1 minute after the 5h rate limit resets. Use this when /budget-check returns ❌ (won't fit) and the user wants to walk away rather than keep planning.

Task

Schedule execution of: $ARGUMENTS

Procedure

1. Validate the plan file

  • $ARGUMENTS must be an absolute file path.
  • If missing or relative, stop and ask the user to save the plan to a file first (suggest ~/.claude/plans/<name>.md).
  • Resolve to an absolute path — the scheduled trigger runs later; relative paths could resolve wrong.

2. Read reset time from session state

Read ~/.claude/.session-state.json:

  • rate_limits.five_hour.resets_at — Unix epoch of next 5h reset

If the cache file is missing or the timestamp >60s stale, stop — don't schedule against stale data.

3. Compute the fire time

  • Target epoch = resets_at + 60 (1-minute buffer past reset)
  • Convert to local time → extract minute, hour, day-of-month, month
  • If target minute is 0 or 30, bump by +1 to avoid the global fleet spike (per CronCreate guidance).
  • Build cron: "<min> <hour> <dom> <month> *"

4. Create the trigger

Call CronCreate with:

  • cron: the expression from step 3
  • prompt: "Execute the plan at <absolute-path>. Read it first, confirm it matches the intent, then work through the steps. Stop and surface anything ambiguous before committing destructive changes."
  • recurring: false (one-shot, auto-deletes after firing)
  • durable: true (persists to disk, survives Claude Code restarts)

5. Confirm to the user

Report:

  • 🗓️ Scheduled for: <local YYYY-MM-DD HH:MM>
  • 📄 Plan: <absolute path>
  • 🆔 Job ID: <id from CronCreate>
  • ⚠️ Note: Claude Code must be running for the trigger to fire. The schedule persists across restarts, but a completely closed app means the trigger queues and fires on next start.
  • 💡 To cancel: CronDelete with the job ID above, or invoke /cancel-scheduled-execution (if built).

6. Length

Keep output under 100 words. One clean confirmation block; no filler.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 2d ago First seen · 53 lines · 13 tokens per session scan A 74b05cad26b3

Subscribe to this mod's changes

execute-at-reset is a command published in the GitHub repository rhan1/crewline (2 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 569 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.