A workflow for taking a coding task from intake and planning through execution, verification, repair, and acceptance. It is designed for one host agent and keeps records of the work and its evidence.

Use it when you need a repeatable, evidence-based process to plan changes, run checks, repair failures, and prove the result passes.

It organizes the steps needed to show that a change works, rather than stopping after the code has been written.

max — Skill for Claude Code and Codex by haoruilee/oh-my-mcode

Install

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.

Any agent

npx skills add haoruilee/oh-my-mcode --skill max

Clone the repo

git clone --depth 1 https://github.com/haoruilee/oh-my-mcode

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/max/github.svg)](https://agentmods.dev/skills/haoruilee/oh-my-mcode/max)

Your own site

<a href="https://agentmods.dev/skills/haoruilee/oh-my-mcode/max"><img src="https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/max/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/haoruilee/oh-my-mcode/max"><img src="https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/max.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,267 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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: 1 finding, up to medium

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 →

medium Agent Snooping · line 36
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00123	$0.01267
Opus 5.5	$0.00049	$0.00507
Sonnet 5.5	$0.00025	$0.00253
Haiku 4.5	$0.00012	$0.00127

Measured 1mo ago against content hash 12d9a7e26634, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

skills/max/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Max Mode

Full verified-delivery loop on one host agent. Role files in agents/ are contracts this same agent must obey, not spawned personas. Never mark Accepted here. Hand acceptance to the verify skill.

中文名：验证交付模式。

Inputs

User goal, constraints, and any files they named.
Workspace root (project being changed). Plugin root is the installed copy, often ~/.minimax/plugins/oh-my-mcode.
State tool: node <plugin-root>/scripts/run-store.mjs (see references/run-store.md). Always write the same .minimax/runs layout. There is no second user-facing CLI to hand off to.
MCP first: if tools omm_run_create, omm_run_show, omm_run_list, omm_status, omm_verify, or omm_inspect exist, use them instead of hand-writing run files or inventing a second store. Do not set PLUGIN_ROOT / PLUGIN_DATA.

Procedure

INTAKE. Restate the goal in one sentence plus out-of-scope. Create the run: node <plugin-root>/scripts/run-store.mjs create --workspace <ws> --goal "<goal>" Persist run_id and the seeded acceptance list (goal-named command or detected test/build) before any host exec. Tell the user the path <ws>/.minimax/runs/<run_id>/ and how we will know we are done.
DISCOVER. CLI max may skip this host exec when the goal already names a file, function, or test command and the workspace has a detected test/build (--discover forces it). plan always discovers. When the explorer does run: set-phase --phase DISCOVER. Load agents/explorer.md. Read-only search and diagnostic commands only. Record risks and test entry points in notes, not in product files.
PLAN. set-phase --phase PLAN. Load agents/planner.md. Write plan.md and tasks.json via write-plan / write-tasks. Every task has one role and depends_on. Acceptance criteria must be commands or diffs a verifier can run without trusting the builder.
PLAN_REVIEW. set-phase --phase PLAN_REVIEW. Show the DAG and acceptance list. If the user asked for a plan only, stop and point them at the plan skill next time. If they asked to ship, continue unless they objected.
EXECUTE. set-phase --phase EXECUTE. Load agents/builder.md. Do one ready task. No scope creep. After the task: append-event --type task_completed --task-id T<n> and capture command output with add-evidence.
VERIFY. set-phase --phase VERIFY. Stop building. Follow skills/verify/SKILL.md and agents/verifier.md. The writer does not grade their own work.
REPAIR. If findings are rejected, a new Builder task is created from structured findings. Return to EXECUTE for that task only, then VERIFY again. Loop until Accepted or the user stops.
ACCEPT. Only the verify skill may leave status=accepted. After that, write evidence-report.
RELEASE. Only if the user asked to commit/PR and status is accepted. Load agents/release.md. Otherwise stop and present summary.md.

Read the full file on GitHub · 64 lines

Files

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.

references/run-store.md 1.9 KB

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.

1mo ago First seen · 64 lines · 123 tokens per session scan A 12d9a7e26634

Subscribe to this mod's changes

max is a skill published in the GitHub repository haoruilee/oh-my-mcode (51 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,267 once invoked, about $0.0005 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 2026-08-30.

Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens