Install
$ agentstack add skill-waitdeadai-minmaxing-opussonnet Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/opussonnet
Run the optional Claude-only workflow for:
$ARGUMENTS
Mode banner:
Claude Code opusplan is the requested model route.
Opus 4.7 is pinned for planning and judgment.
Sonnet 4.6 is pinned for execution.
MiniMax is not required for this optional route.
Contract
- This is a suggested alternative, not the standard default. The default
/opusworkflow route remains Claude/Opus judgment plus MiniMax-M2.7-highspeed execution.
- It is also available as
/opusworkflow --model-profile opussonnetor the
backward-compatible /opusworkflow --executor-provider claude-sonnet.
- Use the same governed
/workflowlifecycle: research brief, SPEC, bounded
implementation, /introspect, /verify, and command-backed closeout.
- Use Claude Code's
opusplanbehavior for the interactive session when
available: Opus in plan mode, Sonnet in execution mode.
- Pin aliases through local ignored settings:
ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-7 and ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-4-6.
- Do not claim Opus or Sonnet runtime identity unless
/status, a runtime
sentinel, or a run artifact proves it for the current account.
- Do not read
.env,.env.*,.claude/settings.local.json,
.claude/*.local.json, secrets/**, private credentials, customer artifacts, or MiniMax key files.
- If the account lacks Opus access, stop and diagnose. Do not silently pretend
the Opus planner ran.
Command
Prepare artifacts through the same workflow wrapper:
bash scripts/opussonnetworkflow.sh --task "$ARGUMENTS"
Runtime planner execution remains explicit:
bash scripts/opussonnetworkflow.sh --task "$ARGUMENTS" --execute-planner
Install
Clean/new folder:
curl -fsSL https://raw.githubusercontent.com/waitdeadai/minmaxing/main/setup.sh | bash -s -- --mode opussonnet
Existing project or harness update:
curl -fsSL https://raw.githubusercontent.com/waitdeadai/minmaxing/main/setup.sh | bash -s -- --import-existing --mode opussonnet
Then run:
claude
/opussonnet "build or fix the thing"
Equivalent static artifact preparation:
bash scripts/opusworkflow.sh --task "build or fix the thing" --model-profile opussonnet
Anti-Patterns
- Presenting
opussonnetas the default MiniMax-backed budget strategy. - Claiming Opus 4.7 was used without runtime evidence.
- Leaving a MiniMax base URL in a Claude-only profile.
- Using Opus for broad repetitive execution when Sonnet can do it under the
governed workflow.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: waitdeadai
- Source: waitdeadai/minmaxing
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.