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 skills add jmagly/aiwg --skill mission-controlgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/mission-control)<a href="https://agentmods.dev/skills/jmagly/aiwg/mission-control"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/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.
<a href="https://agentmods.dev/skills/jmagly/aiwg/mission-control"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/mission-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00026 | $0.01495 |
| Opus 5 | $0.00013 | $0.00747 |
| Sonnet 5 | $0.00005 | $0.00299 |
| Haiku 4.5 | $0.00003 | $0.00150 |
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 9d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission Control
You orchestrate multi-loop background operations using the Mission Control dashboard.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "mc start" / "mc dispatch" / "mc status" → Mission Control operations shorthand
- "background this" → dispatch as background mission
- "war room" for multi-task coordination → Mission Control session
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Background tasks | "run these tasks in the background" | Start session + dispatch |
| Parallel orchestration | "orchestrate X and Y in parallel" | Start session + dispatch each |
| Monitor loops | "monitor background tasks" | aiwg mc status or aiwg mc watch |
| Start session | "start a mission control session" | aiwg mc start |
| Check status | "how are the background tasks doing?" | aiwg mc status --json |
| Stop missions | "stop background work" | aiwg mc stop |
Behavior
When triggered:
-
Determine intent:
- Starting new background work →
aiwg mc start+aiwg mc dispatch - Checking on existing work →
aiwg mc status - Stopping work →
aiwg mc stop
- Starting new background work →
-
For new background orchestration — Mission Control has a four-step lifecycle: start → dispatch → run → status. Missions stay
queueduntilmc runlaunches them as ralph loops; status syncs back to mc.session.json automatically whenmc statusormc watchis called.Apply the LFD loop-control contract before dispatching long-running or eval-driven missions:
- Give each mission a measurable completion criterion and at least one mechanical verifier; self-report is secondary evidence.
- Declare hard limits for iterations, wall-clock, token/tool/spend budgets where the surface can observe them. Budget exhaustion stops the mission and emits a best-output report instead of continuing randomly.
- Record the pre-change hypothesis, expected failure mode, distinguishing diagnostic, and structural variant for each retry cycle.
- After flat/non-improving cycles, require a structurally different approach within the configured exploration quota.
- For eval/holdout missions, expose only aggregate score/probe/status or VOID to workers; keep holdout answers and detailed lint diagnostics outside optimizer-readable mission output.
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.
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.
- 9d ago First seen · 164 lines · 26 tokens per session scan A 0ed4115fb91d
mission-control is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,495 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 2026-08-30.
Other skills, from other repositories
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-class-cycle
Run one DOS plan-class lifecycle tick from the workspace [lifecycle] table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.