A procedure for reopening an unfinished Oh My MiniMax Code run and restoring its saved phase and task. It continues a previous run instead of starting a new one.

Use it when you need to continue the latest run or a specified run in the same workspace.

It prevents losing track of the work already completed, the remaining tasks, and the run’s stored decisions.

resume — Skill for Claude Code and Codex by haoruilee: A procedure for reopening an unfinished Oh My MiniMax…

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.

agentmods

npx agentmods add skills/haoruilee/oh-my-mcode/resume

Any agent

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

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/resume.svg)](https://agentmods.dev/skills/haoruilee/oh-my-mcode/resume)

Your own site

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

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 713 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00117	$0.00713
Opus 5	$0.00059	$0.00357
Sonnet 5	$0.00023	$0.00143
Haiku 4.5	$0.00012	$0.00071

Measured 4d ago against content hash 5f74cac5e738, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume 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.

skills/resume/SKILL.md · 61 lines

What it actually says

Resume Run

Never start a new goal. If there is no run to load, stop and tell the user to say max mode: <task>.

This skill does not register host /resume. Host /resume continues a MiniMax session. This skill restores <workspace>/.minimax/runs/<run_id>/.

中文名：恢复运行。

Inputs

run_id or "latest run in this workspace".
Workspace root.
On-disk artifacts under .minimax/runs/<run_id>/.
State tool: node <plugin-root>/scripts/run-store.mjs.
MCP first: if omm_run_show / omm_run_list / omm_status exist, use them instead of hand-writing run files. Host /resume is still session resume — this skill restores .minimax/runs/<run_id>/. Reuse run.json.host_session_id when opening the TUI (mcode --session <id> or mcode --continue).

Procedure

list --workspace <ws> or show --latest. Identify the run. If multiple and the user did not choose, ask — do not guess a different goal.
Read run.json, plan.md, tasks.json, last findings.json, and the tail of events.jsonl.
append-event --type run_resumed --payload '{"from_phase":"<phase>"}'.
Continue the stored phase, not a restart:
- PLAN / PLAN_REVIEW → plan rules (no product edits).
- EXECUTE / REPAIR → max Builder for the current unfinished task only.
- VERIFY → verify.
- ACCEPT → show summary.md; RELEASE only if asked.
Keep the same run_id. Do not call create.

Output contract

Confirmation of run_id, restored phase, current task, and the next action.
Subsequent writes go to the same run directory.

Failure handling

Corrupt run.json: report the parse error. Do not invent state.
Goal in the user's message disagrees with run.json.goal: refuse to silently switch; they must start a new max-mode run.

Examples

User: resume run_01K3H7WQ0R8SAMPLEAUTH

Load that directory and continue its phase.

User: resume our work — actually also add billing

New goal. Do not fold it into the old run.

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.

4d ago First seen · 61 lines · 117 tokens per session scan A 5f74cac5e738

Subscribe to this mod's changes

resume is a skill published in the GitHub repository haoruilee/oh-my-mcode (51 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 713 once invoked, about $0.0006 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 2026-08-30.

Productivity

systematic-debugging

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

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 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