mission-resume

mission-resume is a command for coding agents from rajconnects/founder-stack. It costs 49 tokens per session (760 once invoked), scanned A, original, MIT.

A command for continuing a paused or blocked autonomous software mission from its saved state.

In plain words
What is it for?
It is for reloading mission state, updating its heartbeat, recording the resume event, and handling missions that are still blocked or already finished.
Why use it?
It restores the mission's context after a session ends, crash, or human intervention, and checks whether the mission is allowed to continue.

Command

Part of the founder-stack plugin — 21 commands, 13 agents shipped together

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/rajconnects/founder-stack/mission-resume
Clone the repo
git clone --depth 1 https://github.com/rajconnects/founder-stack

Or install founder-stack, the plugin that ships this one along with the rest of its 21 commands, 13 agents.

Wrote 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.

agentmods badge for mission-resume

README.md
[![agentmods](https://agentmods.dev/badge/commands/rajconnects/founder-stack/mission-resume.svg)](https://agentmods.dev/commands/rajconnects/founder-stack/mission-resume)
Your own site
<a href="https://agentmods.dev/commands/rajconnects/founder-stack/mission-resume"><img src="https://agentmods.dev/badge/commands/rajconnects/founder-stack/mission-resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 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 $0.00049 $0.00760
Opus 5 $0.00024 $0.00380
Sonnet 5 $0.00010 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 4d ago against content hash ba1c54daebba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mission-resume 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 4d 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.

workflow-v1/commands/mission-resume.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are resuming an in-flight mission in a fresh session. The prior autonomous-loop conversation is gone; everything we need is in state.json.

Arguments: $ARGUMENTS

Steps

  1. If $ARGUMENTS is empty: print ERROR: /mission-resume requires a mission id. Run /mission-status to see active missions. and stop.

  2. Read .claude/project.jsonmission_root. Confirm <mission_root>/<id>/state.json exists. If not, print ERROR: no mission state found at <path>. and stop.

  3. Read the state. Validate:

    • status is one of running, paused, blocked. If completed or aborted: refuse with Cannot resume <id> — status is <status>. and stop.
    • If status: blocked: print the last 5 lines of log.md and the most recent handoff/scrutiny verdict, then ask: Resume anyway? (yes/no). On no: stop.
  4. Synchronously re-sync state (this is small enough to inline — no separate procedure file):

    • Set resume_requested: false if it was true.
    • Update last_heartbeat to now.
    • Save state atomically (Write to state.json.tmp, then Bash mv state.json.tmp state.json).
    • Append to log.md: <timestamp> | mission resumed by /mission-resume.
  5. Print:

    Mission <id> resumed.
      Status:  <status>
      Step:    feature <fid> | <current_step>
      Caps:    <retry_counts[<fid>:worker]>/<caps.max_dispatches_per_feature> retries used
    
    To continue autonomously, type:
      /loop /mission-tick <id>
    
  6. If state.pace == "cron": invoke the /schedule skill via the Skill tool to re-create the routine named mission-<id> (the original may or may not still exist — /schedule create should be idempotent or the skill should handle "already exists" gracefully; if it's strict, list routines first and skip creation if the name already matches). The cron will fire /mission-tick <id> every mission_caps.cron_interval_minutes minutes from now.

    If state.pace == "local": the user will see the instructions from step 5 telling them to type /loop /mission-tick <id>. Nothing more for this command to do.

    /mission-resume itself runs synchronously (no ScheduleWakeup), the same way /mission does. Only /loop /mission-tick (local) or the cron schedule (cron) enables the autonomous tick cadence.

Read the full file on GitHub · 48 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. 4d ago First seen · 48 lines · 49 tokens per session scan A ba1c54daebba

Subscribe to this mod's changes

mission-resume is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 760 once invoked, about $0.0002 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.