Adopt PR Branch Context
pydantic/pydantic-ai-harness
Fills in issue-brief.md and pr-decisions.md for an existing pull request, so you can pick up a PR mid-flight with its linked issue and past review decisions summarized.
mini-harness · initialize or re-initialize a repo's memory under .harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update…
Install Mh Init
$ npx skills add HangYu8123/mini-harness --skill mh-init -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HangYu8123/mini-harness mh-init --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mh-init .claude/skills/mh-init && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .claude/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-initType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HangYu8123/mini-harness --skill mh-init -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HangYu8123/mini-harness mh-init --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mh-init .agents/skills/mh-init && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .agents/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HangYu8123/mini-harness --skill mh-init -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HangYu8123/mini-harness mh-init --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mh-init .cursor/skills/mh-init && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .cursor/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HangYu8123/mini-harness.git --path skills/mh-init--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HangYu8123/mini-harness --skill mh-init -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HangYu8123/mini-harness mh-init --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mh-init .gemini/skills/mh-init && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .gemini/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HangYu8123/mini-harness mh-initInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HangYu8123/mini-harness --skill mh-init -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mh-init .github/skills/mh-init && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .github/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HangYu8123/mini-harness --skill mh-init -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HangYu8123/mini-harness mh-init --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HangYu8123/mini-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mh-init .opencode/skills/mh-init && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mh-init" agent skill from https://github.com/HangYu8123/mini-harness/tree/main/skills/mh-init into .opencode/skills/mh-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mh-init", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mh-init- GitHub stars
- 199
- Token cost
- ~2.6k tokens
- SKILL.md length
- 1,231 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- None found
At a glance
mini-harness · initialize or re-initialize a repo's memory under .harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update…
- Works in 7 steps: Setup · scan → Codebase overview [PARALLEL] — three… → Scripts overview [PARALLEL] — ranked… → …
- Invokes it (/mh-init · $mh-init · /mini-harness init)
- SKILL.md covers Contract, Stages and Red flags
- Calls bash
What it does
Mh Init is an agent skill from HangYu8123/mini-harness. mini-harness · initialize or re-initialize a repo's memory under .harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update log — validated by an isolated verifier; workers' model and effort are selectable per run. Re-runs validate and diff-update existing memory instead of regenerating. Use only when the user invokes it (/mh-init · $mh-init · /mini-harness init).
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Codebase onboarding. It works with Git. The repository describes itself as: A local minimized harness, with simplified output and logs for self-evolve.
When your agent uses it
- Invokes it (/mh-init · $mh-init · /mini-harness init)
- Tasks that involve Codebase onboarding
Example prompts
- “/mh-init”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
- Setup · scan
- Codebase overview [PARALLEL] — three whole-repo perspectives
- Scripts overview [PARALLEL] — ranked repo map
- Verify (isolated)
- Issue scan [PARALLEL] (only after both overviews are on disk)
- Seed the update log
- Report
What it can do on your machine
Read from SKILL.md and the folder at commit baa821f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mh Init loads about 2.6k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 1,231 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,231 words (~2,552 tokens).
“Read .harness/harness.md once per session (pack root: harness/harness.md), .harness/repo_map.md, and — when memory already exists — .harness/reinitialize.md. Documentation only: no source changes. One todo per stage.”
- name
- mh-init
- disable-model-invocation
- true
- argument-hint
- [repo: path] [preserve: files or docs] [subagent_model: <id|inherit>] [subagent_effort: <inherit|low|medium|high|xhigh|max>] — absent dials use the…
Files
Just SKILL.md in skills/mh-init of HangYu8123/mini-harness.
Open the folder on GitHubat commit baa821f
Compare with similar skills
Mh Init next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mh Init this skillHangYu8123/mini-harness | 199 | — | ~2.6k | Automated safety check: Pass | None | |
| Adopt PR Branch Contextpydantic/pydantic-ai-harness | 952 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Basemind Code ContextGoldziher/basemind | 108 | — | ~2.6k | Automated safety check: Pass | MIT | |
| basemind CLI Codebase NavigatorGoldziher/basemind | 108 | — | ~2k | Automated safety check: Pass | MIT | |
| Codebase Onboardingaffaan-m/ECC | 276k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything | 86k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
- Official
Basemind Code Context
Goldziher/basemind
Answers structural questions about a repository, such as where a symbol is defined, what calls it and what changed recently, through the basemind MCP server.
basemind CLI Codebase Navigator
Goldziher/basemind
Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.
Codebase Onboarding
affaan-m/ECC
分析一个陌生的代码库，并生成一个结构化的入门指南，包括架构图、关键入口点、规范和一个起始的CLAUDE.md文件。适用于加入新项目或首次在代码仓库中设置Claude Code时。
Codebase Knowledge Graph Q&A
Egonex-AI/Understand-Anything
Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.
Understand Explain
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
More from HangYu8123/mini-harness
All 8 skills in this repoBreakdown PR
HangYu8123/mini-harness
Plan and optionally execute a large pull request split into small stacked PRs.
Code Review And Quality
HangYu8123/mini-harness
Multi-axis, review-only code review of a diff across six axes — request achievement, correctness, readability/simplicity, architecture, security, and performance — with severity-labelled findings.
Code Simplification
HangYu8123/mini-harness
Simplify code for clarity while preserving exact behavior — reduce nesting, split long functions, remove redundancy and dead code, and fix unclear names.
Mh Loop
HangYu8123/mini-harness
mini-harness · repeat a pass toward a verifiable goal until a check passes or a safety stop fires — spec → validate → confirm → loop (pass · observe · exit check · ledger) → review → record.
Mh Wiki
HangYu8123/mini-harness
mini-harness · consolidate execution trajectories (.harness/exectraj/) into repoinfo/harnesseffect.md — which parts of the harness helped or hurt, root causes, and one proposed change at a time.
Mini Harness
HangYu8123/mini-harness
mini-harness · a supplementary layer over Claude Code and Codex — tags the task, runs online-researcher / diversifier / devils-advocate in addition to the native flow when a trigger fires, keeps a…
Related
Works with
Categories
Questions about Mh Init
What does Mh Init do?
mini-harness · initialize or re-initialize a repo's memory under .harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update…. Mh Init is an agent skill from HangYu8123/mini-harness.harness/repoinfo/ with a multi-agent pass — three-perspective codebase overview, ranked scripts map, issue scan, git-seeded update log — validated by an isolated verifier; workers' model and effort are selectable per run.
When should I use Mh Init?
Mh Init fits situations like: invokes it (/mh-init · $mh-init · /mini-harness init); tasks that involve Codebase onboarding.
How do I install Mh Init in Claude Code?
Run `npx skills add HangYu8123/mini-harness --skill mh-init -a claude-code`. Or copy the skill folder (skills/mh-init in HangYu8123/mini-harness) into .claude/skills/mh-init in your project. Claude Code loads it when a task matches its description.
How do I install Mh Init in Codex?
Run `npx skills add HangYu8123/mini-harness --skill mh-init -a codex`. Or copy the skill folder (skills/mh-init in HangYu8123/mini-harness) into .agents/skills/mh-init in your project. Codex loads it when a task matches its description.
Can I use Mh Init in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HangYu8123/mini-harness --skill mh-init -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mh-init, .gemini/skills/mh-init, .github/skills/mh-init and .opencode/skills/mh-init in your project.
What does Mh Init need to run?
Going by SKILL.md and its folder, Mh Init needs the command-line tools its instructions call (bash).
Does Mh Init access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Mh Init safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Mh Init use?
No licence was found for Mh Init or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Mh Init use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Mh Init?
Skills that share tags, products or a category with Mh Init: Adopt PR Branch Context (pydantic/pydantic-ai-harness, 952 stars), Basemind Code Context (Goldziher/basemind, 108 stars), basemind CLI Codebase Navigator (Goldziher/basemind, 108 stars) and Codebase Onboarding (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mh Init?
HangYu8123 (a GitHub user) maintains it in HangYu8123/mini-harness, which has 199 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 22, 2026.
Source: HangYu8123/mini-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.