MiMoCode is a terminal-based AI coding assistant that reads and writes code, runs commands, manages Git, and remembers project context across sessions. Developers use it to work with software projects through a command-line interface and connect it to language-model providers; the catalogue includes skills and instructions for it.
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.
git clone --depth 1 https://github.com/XiaomiMiMo/MiMo-Codenpx agentmods add skills/xiaomimimo/mimo-code/reportWrote 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/xiaomimimo/mimo-code/report)<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/report"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/report/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.
<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/report"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01664 |
| Opus 5 | $0.00016 | $0.00832 |
| Sonnet 5 | $0.00007 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
compose:report 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 6d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- compose:report — 94% identical, 1 lines differ
- compose:report — 91% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Final Reports
Overview
Consolidate a feature's spec history into a single human-readable final report. The report presents the final implemented state as its primary content — what WAS BUILT, not what was tried. A brief Journey Log at the end captures notable failures and pivots for future designers.
Core principle: Final state first. The reader should understand the feature from this report alone, without reading any spec.
Announce at start: "I'm using the report skill to write the final report for this feature."
Save reports to: the reports/ directory given in the <compose_docs_dir> block of your prompt, as <feature-name>.md
- No date in filename — the report is overwritten in place when the feature evolves
- Git history tracks revisions
- User preferences for report location override this default
Update Semantics
Specs are accumulative (new file per iteration). Final reports are overwrite (same file updated in place):
- If a report already exists for this feature, read it first, then overwrite with updated content
- Append new Journey Log entries from this iteration (don't discard previous entries)
- Update the
specsandplanslists to include any new entries
When to Use
Standard step after implementation is complete and verified — write a final report summarizing what was delivered.
Skip when:
- User explicitly asks to skip the report
- Change is trivially small (single bug fix, typo, config tweak) and not worth documenting
Checklist
- Identify all related specs and plans — find every iteration of this feature's design in specs/ and plans/
- Read the implemented code — understand what actually shipped (code is truth, not specs)
- Draft main sections — What Was Built, Architecture, Usage, Verification (scale each section to complexity: a few sentences if straightforward, detailed for complex features, but never longer than the plan)
- Draft Journey Log — brief flat bullet list, max 5 items
- Assemble report — combine sections, add frontmatter, save to reports/
- Self-review — verify report against code (not specs), check for placeholders, confirm length is proportional to feature complexity
- Mark specs and plans — prepend NOTE header to each spec and plan file
- Commit and transition — commit report + markers, invoke compose:merge
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.
- 6d ago First seen · 180 lines · 33 tokens per session scan A ef966f19816e
compose:report is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,997 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,664 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.