mission

A command for starting a long-running software mission with a defined goal, validation contract, and repeated work-and-review cycles.

In plain words
What is it for?
Use it to launch autonomous implementation work from a written goal or GitHub issue, choose local or scheduled pacing, and optionally create a pull request after completion.
Why use it?
It turns a broad task into an explicitly checked workflow and can continue through local or scheduled ticks. It can also prepare an automatic pull request when enabled.

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/rajconnects/founder-stack/mission
Clone the repo
git clone --depth 1 https://github.com/rajconnects/founder-stack
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,116 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 $0.00050 $0.01116
Opus 5 $0.00025 $0.00558
Sonnet 5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash a12a99b67846, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mission 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.

workflow-v1/commands/mission.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 kicking off a new Founder Stack v1 autonomous mission. This command runs orchestration logic directly in the main agent thread (not via a sub-agent), so that downstream Task tool dispatches to feature-worker, scrutiny-validator, design-auditor, schema-analyst, user-flow-tester, docs-auditor, and memory-broker actually work — Claude Code blocks sub-agents from spawning further sub-agents.

Arguments: $ARGUMENTS

Steps

  1. Parse arguments. Recognized:

    • --from-issue <url> — fetch a GitHub issue's title+body and use it as the goal seed (the procedure authors the contract from it).
    • --pace local|cron — local (default; ScheduleWakeup inside /loop, requires Claude Code stay open) or cron (routes ticks through /schedule so missions survive laptop sleep).
    • --auto-pr — when the mission completes, automatically push the branch and gh pr create with an assembled body. Default off; the procedure prints the suggested command for the user to run.
    • Remaining positional text is the goal string. Strip the flags first.

    If neither a goal string nor --from-issue is provided, print:

    /mission requires a goal. Examples:
      /mission "build a counter component with persisted state"
      /mission --from-issue https://github.com/<org>/<repo>/issues/42
    Optional: --pace local (default) | --pace cron, --auto-pr
    

    Stop.

  2. Read .claude/project.json. Confirm mission_root is set (default missions/). If the project hasn't been configured for v1 yet, print one line directing the user to copy .claude/project.example.v1.json keys into their project.json, then proceed with defaults.

  3. Read .claude/procedures/v1/mission-new.md and execute it in this main agent thread. That procedure scopes the goal with the user, authors the contract, gets approval, creates the worktree, and initializes state.json. It prints its own user-facing output directly (scoping questions, contract preview, approval prompt, pace-specific final instructions) — do not re-print. Pass it the parsed values:

    • GOAL: the parsed goal string (or "from-issue" if --from-issue was used)
    • ISSUE_URL: the URL if --from-issue, else "none"
    • PACE: local or cron
    • AUTO_PR: true or false

    When the procedure finishes, capture the returned mission_id and pace (the procedure's step 11 returns a one-line summary containing both).

  4. If pace == "cron": invoke the /schedule skill via the Skill tool to create a recurring routine that fires /mission-tick <mission_id> every mission_caps.cron_interval_minutes (default 10) minutes. The routine name should be mission-<mission_id> so subsequent commands (/mission-tick, /mission-abort, /mission-resume) can find and delete it by name. If routine creation fails, surface the error and tell the user they can fall back to /loop /mission-tick <id> for local pacing. Do not delete the mission directory on cron failure — the contract is still valid; the user just loses the cron-driven path.

    If pace == "local": the procedure's printed instructions already told the user to type /loop /mission-tick <id>. Do nothing further.

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. 2d ago First seen · 48 lines · 50 tokens per session scan A a12a99b67846

Subscribe to this mod's changes

mission is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,116 once invoked, about $0.0003 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.