minimax

minimax is a skill for Claude Code from terrylica/cc-skills. It costs 40 tokens per session (5,481 once invoked), scanned A, original, MIT.

A production integration guide for MiniMax M-series models through their OpenAI-compatible chat API. It documents differences in request handling, responses, errors, and model limitations.

In plain words
What is it for?
Use it when wiring MiniMax into an application, choosing where to use Python or validators, or handling reasoning output and API errors.
Why use it?
It helps prevent integration bugs caused by API behaviours that differ from the OpenAI interface they resemble.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [`../m3/SKILL.md`](../m3/SKILL.md) and the evidence doc.

Part of the minimax plugin — 2 skills shipped together , and of cc-skills

Good fit Use it when wiring MiniMax into an application, choosing where to use Python or validators, or handling reasoning output and API errors.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/terrylica/cc-skills
agentmods
npx agentmods add skills/terrylica/cc-skills/minimax

Made for: Claude Code.

Or install minimax, the plugin that ships this one along with the rest of its 2 skills.

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 minimax

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/minimax/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/minimax)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/minimax"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/minimax/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 minimax

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/minimax"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/minimax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 310
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • medium Data Exfiltration · line 9
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 304
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Prompt Injection · line 26
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 259
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Rogue Agent · line 296
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 331
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 310
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00040 $0.05481
Opus 5 $0.00020 $0.02740
Sonnet 5 $0.00008 $0.01096
Haiku 4.5 $0.00004 $0.00548

Measured 5d ago against content hash 98cc68c34234, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minimax scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -X POST "$OPENAI_BASE_URL/chat/completions" \
plugins/minimax/skills/minimax/SKILL.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax M-series Production Wiring

OpenAI-compatible chat-completion endpoint at https://api.minimax.io/v1 with the M2.7-highspeed reasoning model (premium tier as of 2026-04-29). LOOKS LIKE OPENAI but silently drops 6 OpenAI parameters and exposes <think> reasoning traces inside content. Beyond chat-completion, the API is MiniMax-native (different URLs, different body shapes, different error envelopes — HTTP 200 + base_resp.status_code instead of HTTP 4xx).

The model itself is a competent qualitative judge + theory explainer + tool orchestrator for finance/quant work, but cannot do raw math on realistic data sizes (saturates reasoning budget) and hallucinates plausible details under input uncertainty (6 documented instances). For production: pair it with Python for math, sandbox validators for code, and deterministic detectors for pattern recognition.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues. Source-of-truth campaign archive: ~/own/amonic/minimax/ (read-only reference; do not modify from this skill).

🆕 MiniMax-M3 is live (2026-06-01). This file covers M2.7. For M3 — native vision, reasoning_split clean output, response_format acceptance, ~1M input ceiling (reliable retrieval ≤ ~256K) / 524K output cap, n=1, and the docs-vs-reality discrepancies — use the sibling skill ../m3/SKILL.md and the evidence doc ../../references/M3-EMPIRICAL.md. The defensive snippets below (<think> strip, base_resp retry, cached-token reader) apply to M3 unchanged.


When to use M2.7 vs not — the decision table

Workload Verdict Why
Tagging / classification (5-15 token outputs) ✅ Use plain MiniMax-M2.7 Plain is 2.5× faster than -highspeed for short outputs (cross-over at ~150 tokens).
Summarization / long-form generation ✅ Use -highspeed -highspeed wins at >150 tokens. ~50 TPS asymptote (NOT the 100 TPS plan claim).
Trade signal JSON output ✅ Production-ready 6/6 verified across L1+L2+L3 layers with strict system prompt. Confidence well-calibrated.
Financial theory explanation ✅ Graduate-level Black-Scholes derivations, FTAP, KKT, vol skew microstructure all correct.
Long-context retrieval (≤ 30K tokens) ✅ 4/4 needle retrieval NO "lost in the middle" effect. Perfect retrieval at 10/50/85/98% positions.
Tool orchestration (agent loop) ✅ 4/4 correct selection Parallel + chained tool calls work. Refuses irrelevant queries gracefully.
Math / Black-Scholes / Sharpe on N≥50 returns ❌ DO NOT USE Saturates 8-16K reasoning tokens; route to Python (numpy/scipy/cvxpy).
QP / constrained optimization (Markowitz) ❌ DO NOT USE Same saturation pattern. Use scipy.optimize / cvxpy.
Risk metrics on realistic data (N=252 returns) ❌ DO NOT USE Even SINGLE metric saturates. Pre-summarize aggregates before passing.
Chart pattern recognition ❌ DO NOT USE Hallucinates patterns in pure noise. Use TA-Lib / CV / classical algos.
Code generation (final, deployable) ⚠️ Scaffold-only Compiles 100%, runs 0% on first try (hallucinates library imports). Sandbox-validate.
Vision / image input ❌ NOT SUPPORTED M2.7 is text-only. image_url silently dropped at INPUT level.
TTS / video ⚠️ Plan-gated Endpoints exist (/v1/t2a_v2, /v1/video_generation) but error 2061 on Plus-High-Speed.
Embeddings (bulk RAG) ⚠️ RPM-tight /v1/embeddings accessible but rate-limited beyond ~5 calls. Use local embeddings.

Read the full file on GitHub · 343 lines

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. 5d ago First seen · 343 lines · 40 tokens per session scan A 98cc68c34234

Subscribe to this mod's changes

minimax is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 5,481 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.