mission-control

mission-control is a skill for Codex from uchicago-dsi/ai-sci-skills. It costs 65 tokens per session (1,632 once invoked), scanned A, original, MIT.

A workflow for coordinating several long-running agents or workers while keeping one shared goal and current view of their progress.

In plain words
What is it for?
Use it to supervise tmux or managed agents, assign bounded tasks, inspect their actual work, reconcile corrections, and steer the next action.
Why use it?
It reduces confusion caused by stale instructions, disconnected worker summaries, and unresolved tasks that no longer matter.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to supervise tmux or managed agents, assign bounded tasks, inspect their actual work, reconcile corrections, and steer the next action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uchicago-dsi/ai-sci-skills/mission-control
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.

Any agent
npx skills add uchicago-dsi/ai-sci-skills --skill mission-control
Clone the repo
git clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skills

Made for: Codex.

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-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/mission-control/github.svg)](https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/mission-control)
Your own site
<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/mission-control"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/mission-control/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.

agentmods 80×15 button for mission-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/mission-control"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/mission-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00065 $0.01632
Opus 5 $0.00032 $0.00816
Sonnet 5 $0.00013 $0.00326
Haiku 4.5 $0.00006 $0.00163

Measured 11d ago against content hash 79dd57e5c355, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mission-control 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 11d 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.

skills/mission-control/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission Control

Maintain the global objective while workers execute bounded tasks. Treat steering as a control signal, not a FIFO inbox.

Establish The Current Control State

Before steering, maintain a compact view of:

  • global objective and current decision;
  • each worker's owned task;
  • last verified evidence or artifact;
  • current indivisible operation, if any;
  • next state-changing action;
  • pending correction and whether it is still current.

Inspect the worker's actual pane, log, job, or artifact before relying on its summary. Refresh this state after a user correction, completed experiment, failure, commit, submission, or other decision-changing event.

Keep The Mission State Disposable

If the campaign needs a state file, make it a current-state dashboard, not a second lab notebook.

  • Update it in place; do not append chronology.
  • Keep it short, ideally under 80 lines. Delete resolved tasks, stale job states, superseded corrections, and metrics that no longer affect a decision.
  • Include only the global objective and current decision, active baseline, worker ownership and state, live jobs or indivisible operations, blockers, next state-changing actions, and links to authoritative artifacts.
  • Store commands, detailed metrics, provenance, failures, and historical reasoning in the lab notebook or experiment report. Link those records instead of copying them.
  • If the dashboard starts accumulating history, rebuild it from current evidence rather than editing the accumulated narrative.

The lab notebook answers "what happened?" The mission-state file answers "what is true now, and what happens next?"

Classify Every Steering Message

Put steering in one of three classes:

  1. Interrupt now: the message changes direction, invalidates an assumption, prevents unsafe or wasted work, or supersedes the worker's current task.
  2. Gate the next mutation: the worker may finish its current indivisible operation, but must incorporate the correction before another commit, submission, browser/API call, transfer, deletion, or experiment.
  3. Queue for a natural boundary: the message is additive, nonurgent, and remains useful even if the current task completes first.

Read the full file on GitHub · 180 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 180 lines · 65 tokens per session scan A 79dd57e5c355

Subscribe to this mod's changes

mission-control is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,632 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.

Related

Other skills, from other repositories