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.
npx agentmods add skills/spacedock-dev/spacedock/first-officernpx skills add spacedock-dev/spacedock --skill first-officergit clone --depth 1 https://github.com/spacedock-dev/spacedockWrote 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/skills/spacedock-dev/spacedock/first-officer)<a href="https://agentmods.dev/skills/spacedock-dev/spacedock/first-officer"><img src="https://agentmods.dev/badge/skills/spacedock-dev/spacedock/first-officer.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00578 |
| Opus 5 | $0.00017 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
first-officer 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If this skill is invoked directly in a non-interactive run and the prompt names a specific entity to process, enter single-entity mode immediately:
- scope work to that entity only
- follow the shared single-entity rules from the operating contract and any runtime-specific bounded-stop rules
- keep running until the shared/runtime-specific stop condition for the requested bounded outcome is satisfied
- do not treat an initial rejection as terminal when the workflow's feedback flow expects a routed follow-up
- if the prompt only names the entity and does not explicitly request terminal completion, treat the runtime's bounded routed-reuse stop rule as sufficient
- before the final response, explicitly shut down any worker that is no longer needed for later routing or gate handling
- once the bounded stop condition is satisfied, send one concise final response and exit immediately
How the first officer operates
You are dispatcher, responsible for making sure the work is done by the crew. What awesome looks like:
- Begin with the end; be clear about the value.
- Do the hardest things first; de-risk while it is cheap.
- Communicate and act concisely, choose the simplest approach, JFDI.
Operating contract
The skill loader supplies the absolute base directory for this first-officer skill when it opens this file. Retain that exact directory as {first_officer_base} for the session. A deferred first-officer core may only append the one literal /references/... suffix named at its load point; never derive this base from cwd, discover it through a wrapper skill, try alternate install paths, or search the filesystem.
Mandatory load boundary: the shared core's deferred write/merge reads are action preconditions, not optional background. No FO-authored mutation starts before the write read completes. No terminal or merge-mod recovery action starts before the merge read completes; when terminalization also mutates state, complete write first and merge second.
@references/first-officer-shared-core.md
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/claude-first-officer-runtime.md 4.7 KB
- references/claude-fo-dispatch.md 18 KB
- references/codex-first-officer-runtime.md 8.1 KB
- references/first-officer-shared-core.md 22 KB
- references/fo-dispatch-core.md 31 KB
- references/fo-install.md 3.1 KB
- references/fo-merge-core.md 4.2 KB
- references/fo-write-core.md 6.9 KB
- references/pi-first-officer-runtime.md 7.6 KB
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.
- 5d ago First seen · 39 lines · 35 tokens per session scan A 32389cb5e666
first-officer is a skill published in the GitHub repository spacedock-dev/spacedock (76 stars, last pushed 6d ago), licensed Apache-2.0. It adds 35 tokens to every session and 578 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 2026-08-30.
Other skills, from other repositories
archon
Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.
fleet
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.
daemon
Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget…
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.