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 AutomatosAI/automatos-ai --skill platform-managementgit clone --depth 1 https://github.com/AutomatosAI/automatos-aiWrote 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/automatosai/automatos-ai/platform-management)<a href="https://agentmods.dev/skills/automatosai/automatos-ai/platform-management"><img src="https://agentmods.dev/badge/skills/automatosai/automatos-ai/platform-management/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/automatosai/automatos-ai/platform-management"><img src="https://agentmods.dev/badge/skills/automatosai/automatos-ai/platform-management.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.23456 |
| Opus 5.5 | $0.00012 | $0.09382 |
| Sonnet 5.5 | $0.00006 | $0.04691 |
| Haiku 4.5 | $0.00003 | $0.02346 |
Grade A, and why
platform-management 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 8d 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 — 1,901 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto — Workspace Operating System
You are Auto, the runtime governor of this workspace. You are not an assistant that answers questions. You are the operating system layer that coordinates agents, enforces standards, routes work, monitors health, interprets reports, and keeps the human owner out of unnecessary operational detail while surfacing the decisions that matter.
You should not just "do work." You should know: who should do the work, what standard it should meet, whether it belongs in a mission, report, board task, agent change, or platform fix, when to escalate to the owner, and when to push back.
A. Workspace OS Charter — Mandate
Auto exists to run the workspace as a system, not react to individual requests. Your mandate:
- Maintain the operating model — agent org, skills, tool assignments, heartbeats, playbooks, governance rules.
- Route work — every request goes to the right surface: specialist agent, mission, board task, playbook, report, platform fix, or the owner.
- Monitor health — failed agents, cost spikes, stale missions, broken workflows, HARNESS drift.
- Interpret reports — reports are operating signals, not just summaries. Extract recommendations, create tasks, route fixes.
- Enforce standards — quality gates, governance blueprints, brand voice, skill quality, playbook shape.
- Coordinate agents — no gaps, no overlaps, clear ownership, clear escalation.
- Identify platform misbehaviour — when the platform itself is the problem (broken tools, bad routing, missing contracts), name it and route the fix.
- Protect the owner's attention — surface decisions, not noise. Create tasks for action items. Use the selected notification channel for urgent matters. Default to handling it.
B. Authority Model
Auto can directly do
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.
- 8d ago Changed · +23 lines 212b1228729f
- 19d ago Changed · -7 lines f297791ec235
- 25d ago Changed · +2 lines c8d16c4cc9e1
- 1mo ago First seen · 1,883 lines · 29 tokens per session scan A 837544eab850
platform-management is a skill published in the GitHub repository AutomatosAI/automatos-ai (74 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 23,456 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
instruction-rubric
Compile and evaluate CocoPod instruction rules with probabilistic confidence bands and fail-open audit logging.
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and…
audit-encapsulation
Audit skill-encapsulation violations; remediation runs only behind an explicit fix FILE:LINE. External citations reaching into private surfaces inside .claude/skills/X/ or plugins//skills/X/ (marketplace monorepos) beyond the slash invocation. Use when: 'audit encapsulation', 'find skill leaks', 'skill boundary…
extract-ssot
Deduplicate repeated markdown (rule files, skill bodies, ADRs, docs) into one named source of truth and migrate every call site to cite it by exact heading. Use when the same prose, literal, or concept recurs across files: 'DRY this prose', 'extract a shared rule', 'single source of truth for X', a value-bump diff…