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/mr-tbot/auto-everything/auto-agent-maxnpx skills add mr-tbot/Auto-Everything --skill auto-agent-maxgit clone --depth 1 https://github.com/mr-tbot/Auto-EverythingWrote 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/mr-tbot/auto-everything/auto-agent-max)<a href="https://agentmods.dev/skills/mr-tbot/auto-everything/auto-agent-max"><img src="https://agentmods.dev/badge/skills/mr-tbot/auto-everything/auto-agent-max.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 | $0.00084 | $0.01454 |
| Opus 5 | $0.00042 | $0.00727 |
| Sonnet 5 | $0.00017 | $0.00291 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
auto-agent-max 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-agent-max
Remove the tier ceiling. A subagent may run the same model as the orchestrator when the subtask genuinely warrants it.
Usage: /auto-agent-max — the agent count is yours to judge.
/auto-agent-max 10 — a hard ceiling of ten subagents.
What This Changes, And What It Does Not
It changes exactly one thing: the cap. From the top tier you may now spawn peers, which
/auto-agent-eco forbids.
It does not change the routing discipline. "Max" is not "put everything on the biggest model" — that
is not maximum capability, it is maximum spend with a side of latency. A top-tier agent sent to run
grep across a directory returns the same answer as a cheap one, slower and dearer, and having four
of them queued behind a rate limit is worse than the eco version that finished.
So the question every subagent still has to pass is the same one: what does this task actually need? The difference is only that "the top tier" is now an available answer instead of a forbidden one.
When A Peer-Tier Subagent Is Genuinely Right
Reach for one when the subtask carries the same difficulty as the orchestration:
- Adversarial verification of a consequential claim. Whatever tries to refute a finding should be at least as capable as whatever produced it. If a top-tier agent found it, a top-tier agent should attack it.
- Independent attempts at a hard design, where the value is genuine diversity of approach rather than parallel throughput. Three peers reasoning separately, then judged, beats one attempt iterated when the solution space is wide.
- Deep reasoning over unfamiliar territory — an undocumented protocol, a subtle concurrency defect, a build system misbehaving for non-obvious reasons.
- Work whose failure is expensive and quiet: security review, licensing judgments, anything that ships and misleads if it is wrong.
When It Is Still Wrong, Even Here
- Locating code, inventorying files, running builds, applying a stated edit — these do not improve with a better model, and the queue they create is a real cost.
- Anything where the answer is verifiable by execution. Let something cheap produce it and let the test say whether it is right.
- Padding a fan-out to look thorough. Six peers on a three-agent problem is not rigour, it is six agents rediscovering the same context and then disagreeing about it.
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.
- 4d ago First seen · 109 lines · 84 tokens per session scan A 7265a2d8aead
auto-agent-max is a skill published in the GitHub repository mr-tbot/Auto-Everything (7 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,454 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…