Install Anti-Slop Oxlint Rules
dmmulroy/anti-slop
Installs, updates or migrates the vendored anti-slop Oxlint plugin in a repository, keeping local rule changes and the plugin's license and provenance files.
Generate a customized precommit runner for any ecosystem. An agent skill from sd0xdev/sd0x-harness.
Install Generate Runner
$ npx skills add sd0xdev/sd0x-harness --skill generate-runner -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sd0xdev/sd0x-harness generate-runner --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/sd0xdev/sd0x-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/generate-runner .claude/skills/generate-runner && 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 "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .claude/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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/sd0xdev/sd0x-harness/tree/main/skills/generate-runnerType 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 sd0xdev/sd0x-harness --skill generate-runner -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sd0xdev/sd0x-harness generate-runner --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/generate-runner .agents/skills/generate-runner && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .agents/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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 sd0xdev/sd0x-harness --skill generate-runner -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sd0xdev/sd0x-harness generate-runner --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/generate-runner .cursor/skills/generate-runner && 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 "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .cursor/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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/sd0xdev/sd0x-harness.git --path skills/generate-runner--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 sd0xdev/sd0x-harness --skill generate-runner -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sd0xdev/sd0x-harness generate-runner --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/generate-runner .gemini/skills/generate-runner && 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 "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .gemini/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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 sd0xdev/sd0x-harness generate-runnerInstalls 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 sd0xdev/sd0x-harness --skill generate-runner -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/generate-runner .github/skills/generate-runner && 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 "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .github/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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 sd0xdev/sd0x-harness --skill generate-runner -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sd0xdev/sd0x-harness generate-runner --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/generate-runner .opencode/skills/generate-runner && 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 "generate-runner" agent skill from https://github.com/sd0xdev/sd0x-harness/tree/main/skills/generate-runner into .opencode/skills/generate-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-runner", 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
generate-runner- GitHub stars
- 192
- Token cost
- ~2.1k tokens
- SKILL.md length
- 852 words
- Files
- 2 (incl. references)
- Skills in repo
- 91
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate a customized precommit runner for any ecosystem. An agent skill from sd0xdev/sd0x-harness.
- Works in 5 steps: Detect Ecosystem → Select Template → Customize → …
- : non-Node projects need a runner
- SKILL.md covers Trigger, When NOT to Use, Lint Argument Injection and Workflow, plus 5 more sections
- Calls node and bash
What it does
Generate Runner is an agent skill from sd0xdev/sd0x-harness. Generate a customized precommit runner for any ecosystem. Use when: non-Node projects need a runner, eject from generic runner, customize runner for project. Not for: running precommit (use /precommit), installing runner (handled by auto-install). Output: customized runner script with eject header.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/templates.md`).
It sits in Development, covering Linting and formatting. The repository describes itself as: The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and… The licence is MIT.
When your agent uses it
- : non-Node projects need a runner
- Eject from generic runner
- Customize runner for project
Example prompts
- “/generate-runner”
Requirements
- Python 3
- Node.js
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash(node:*), Bash(chmod:*), Bash(bash:*), Write, AskUserQuestion
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c9a2036. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobBash(node:*)Bash(chmod:*)Bash(bash:*)WriteAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
nodebash
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
Generate Runner loads about 2.1k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 852 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
The full file from sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 852 words, ~2,062 tokens.
Download SKILL.mdSave it as
.claude/skills/generate-runner/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- generate-runner
- description
- Generate a customized precommit runner for any ecosystem. Use when: non-Node projects need a runner, eject from generic runner, customize runner for project. Not for: running precommit (use /precommit), installing runner (handled by auto-install). Output: customized runner script with eject header.
- allowed-tools
- Read, Grep, Glob, Bash(node:*), Bash(chmod:*), Bash(bash:*), Write, AskUserQuestion
Generate Runner
Trigger
- Keywords: generate runner, create runner, custom runner, eject runner, runner for python, runner for rust, runner for go
When NOT to Use
| Need | Use Instead |
|---|---|
| Run precommit checks | /precommit or /precommit-fast |
| Install existing runner | /project-setup (auto-installs) |
| Configure the shipped runner's lint globs | Check first that the runtime runner has no @generated_at header, then edit .claude/runner-config.json — and set lintArgMode for the same script role, or the globs stay inert (see § Lint Argument Injection) |
Lint Argument Injection
Scope: the runners this plugin ships — scripts/precommit-runner.js and
scripts/verify-runner.js. What /precommit, /precommit-fast and /verify actually execute is
the runtime copy at .claude/scripts/*, installed by /install-scripts. A runner generated by
this skill is written to the same path but is user-owned: its template does not append lint
arguments, so lintGlobs / lintArgMode have no effect on it. The discriminator is the eject
header (§ Step 4) — all three of @generated_at, @plugin_version, @template, each on its own
line with a value, in the opening comment block. Read the file before configuring it.
Known limitation. A project that installed a runner before this fix keeps running the old
version, which passes ESLint-only flags into whatever lint script the repo declares — a
file-rewriting non-ESLint linter reads them as paths and edits sources. Fixing the plugin source
does not reach that copy, and detecting it reliably needs per-release provenance, which is
deliberately out of scope. Remedy: /install-scripts precommit-runner.js verify-runner.js --force, with --dry-run first to read the write set (the installer copies "scripts +
dependencies" without defining the closure, so the dry run is the authoritative list). The runners
are named rather than swept in by --all, which would force-overwrite every core script; confirm
lib/utils.js — where the fixed runners decide whether to inject — appears in the report.
The shipped runner appends nothing to your lint script unless you ask it to. lintGlobs alone
does nothing; it needs lintArgMode for the same script role.
| Setting | Where | Shape |
|---|---|---|
lintArgMode | .claude/runner-config.json, or package.json → sd0x | {"lint": "eslint"} / {"lint:fix": "none"} — keyed by script role, never a bare string. Accepted values: "eslint" and "none" |
lintGlobs | same two places | ["src/**/*.{ts,tsx,js,jsx}", …] — applied only when that role's lintArgMode is "eslint" |
Precedence, per role: .claude/runner-config.json first, first valid value wins;
package.json → sd0x is the fallback. An unusable value — a bare string, a value outside
eslint/none, a non-role-keyed shape — is warned about and falls through rather than latching,
so "none" in .claude can suppress an opt-in package.json declares. (An unreadable
.claude/runner-config.json warns via loadLintGlobs(); an unreadable package.json stays
silent.)
In package.json, to inject ESLint's flags and globs into lint:fix only:
{ "sd0x": { "lintArgMode": { "lint:fix": "eslint" }, "lintGlobs": ["src/**/*.{ts,js}"] } }precommit reads the lint:fix role; verify reads lint — keyed separately because a repo
routinely runs different engines for each (this one runs markdownlint for lint:fix).
Why it is opt-in. The runner used to inject by default and guess from the script text whether
the recipient was ESLint. markdownlint-cli2 treats every unrecognised argument as a file glob, so
under --fix it rewrote JavaScript as Markdown; one run corrupted 71 files in this repo. Four
successive detection grammars each misclassified something, so detection was removed rather than
deepened.
Workflow
flowchart LR
A[Detect Ecosystem] --> B[Select Template]
B --> C[Customize]
C --> D[Write Runner]
D --> E[Verify]Show full SKILL.md (347 more words)Show less
Step 1: Detect Ecosystem
Scan project root for manifest files:
| Manifest | Ecosystem | Template ID |
|---|---|---|
pnpm-lock.yaml | Node.js (pnpm) | node-pnpm |
yarn.lock | Node.js (yarn) | node-yarn |
package-lock.json or package.json | Node.js (npm) | node-npm |
pyproject.toml | Python | python |
Cargo.toml | Rust | rust |
go.mod | Go | go |
If multiple detected, prefer Node.js > Python > Rust > Go. If none detected, ask user.
Step 2: Select Template
Load template from references/templates.md for the detected ecosystem.
Step 3: Customize
Read project-specific configuration:
| Source | What |
|---|---|
package.json scripts | Lint command, test command, build command |
.claude/runner-config.json | Not read for lint configuration. Neither lintGlobs nor lintArgMode reaches a generated runner — the template does not append lint arguments at all (§ Lint Argument Injection), so listing either here would present an inert value as a customization input |
| Lock file | Package manager selection |
Step 4: Write Runner
Write to .claude/scripts/precommit-runner.js (Node) or .claude/scripts/precommit-runner.sh (non-Node).
A non-Node runner is generated for manual invocation, not for
/precommit./precommit,/precommit-fastand/verifyprobe the.jspath only and execute it on existence; none of them detects a.shrunner today. So a Python, Rust or Go runner generated here is a real, working script that those commands will not run — invoke it directly, or keep the ecosystem's checks in the shipped runner, which orchestrates pytest/cargo/go as first-class steps (skills/precommit/SKILL.md§ Step 2). Teaching the three commands to detect and order a.shrunner is a change to runner dispatch, not to this skill, and is not implied by generating one.
Include eject header:
@generated_at <ISO 8601>
@plugin_version <current version>
@template <template-id>
@ecosystem <ecosystem>Conflict handling: If target file exists, AskUserQuestion with diff preview.
Step 5: Verify
- File written successfully
- Script is executable (non-Node:
chmod +x) - Syntax check, named so it can actually be run:
node --check <path>for the Node runner,bash -n <path>for a shell one
Arguments
| Argument | Description | Default |
|---|---|---|
--ecosystem <name> | Force ecosystem (skip detection) | auto-detect |
--output <path> | Custom output path | Ecosystem-dependent, per § Step 4: .claude/scripts/precommit-runner.js for Node, .claude/scripts/precommit-runner.sh otherwise |
--force | Overwrite existing without asking | off |
Output
## Generated Runner
- Ecosystem: <detected>
- Template: <template-id>
- Output: <path>
- Package manager: <pm>
The generated runner is **user-owned** — plugin updates will not overwrite it.
Edit freely to customize for your project.Verification
- Ecosystem correctly detected
- Template matches ecosystem
- Eject header present with correct metadata
- Runner script is valid (no syntax errors)
- Existing file conflict handled (ask or --force)
References
- Per-ecosystem templates:
references/templates.md
Examples
Input: /generate-runner
Action: Detect Node.js (yarn) → load node-yarn template → customize → write .claude/scripts/precommit-runner.js
Input: /generate-runner --ecosystem python
Action: Load python template → customize → write .claude/scripts/precommit-runner.sh
Input: /generate-runner --force
Action: Detect ecosystem → overwrite existing runner without asking© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/generate-runner of sd0xdev/sd0x-harness.
- SKILL.md
- references/templates.md
Open the folder on GitHubat commit c9a2036
Compare with similar skills
Generate Runner 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 |
|---|---|---|---|---|---|---|
| Generate Runner this skillsd0xdev/sd0x-harness | 192 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Install Anti-Slop Oxlint Rulesdmmulroy/anti-slop | 5.2k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Babysit PR To Pass CIsgl-project/sglang | 37k | 2 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Rust Best Practicesfarm-fe/farm | 5.6k | 3 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Go Pedantrychromedp/chromedp | 13k | — | ~3.7k | Automated safety check: Pass | MIT | |
| Kedro Babysitkedro-org/kedro | 11k | — | ~4k | Automated safety check: Pass | Custom licence |
Similar skills
Babysit PR To Pass CI
sgl-project/sglang
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.
Rust Best Practices
farm-fe/farm
Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook.
Go Pedantry
chromedp/chromedp
This skill should be used when the user is writing Go code and needs guidance on Go-specific pedantry: error wrapping with fmt.Errorf and %w, interface design (accept interfaces return structs)…
Kedro Babysit
kedro-org/kedro
Run Kedro's local lint / format / type-check / tests on changed files (uses the project's pre-commit hooks, ruff, mypy, pytest, lint-imports, detect-secrets, Make targets — in the right venv), or…
WooCommerce Markdown Guidelines
woocommerce/woocommerce
Rules for writing and editing markdown in the WooCommerce repository, with the project's markdownlint settings for headings, lists and code blocks.
More from sd0xdev/sd0x-harness
All 91 skills in this repoAdr
sd0xdev/sd0x-harness
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/<feature/adr-<NNN-<title.md with a 3-digit zero-padded…
Load PR Review
sd0xdev/sd0x-harness
Load GitHub PR review comments into AI session — analyze, triage, plan.
Next Step
sd0xdev/sd0x-harness
Change-aware next step advisor. An agent skill from sd0xdev/sd0x-harness.
Obsidian CLI
sd0xdev/sd0x-harness
Obsidian vault integration via official CLI. An agent skill from sd0xdev/sd0x-harness.
Orchestrate
sd0xdev/sd0x-harness
Agent-driven workflow orchestration (v1 report-only). An agent skill from sd0xdev/sd0x-harness.
PR Comment
sd0xdev/sd0x-harness
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review.
Related
Categories
Questions about Generate Runner
What does Generate Runner do?
Generate a customized precommit runner for any ecosystem. An agent skill from sd0xdev/sd0x-harness. Generate Runner is an agent skill from sd0xdev/sd0x-harness. Generate a customized precommit runner for any ecosystem.
When should I use Generate Runner?
Generate Runner fits situations like: : non-Node projects need a runner; eject from generic runner; customize runner for project.
How do I install Generate Runner in Claude Code?
Run `npx skills add sd0xdev/sd0x-harness --skill generate-runner -a claude-code`. Or copy the skill folder (skills/generate-runner in sd0xdev/sd0x-harness) into .claude/skills/generate-runner in your project. Claude Code loads it when a task matches its description.
How do I install Generate Runner in Codex?
Run `npx skills add sd0xdev/sd0x-harness --skill generate-runner -a codex`. Or copy the skill folder (skills/generate-runner in sd0xdev/sd0x-harness) into .agents/skills/generate-runner in your project. Codex loads it when a task matches its description.
Can I use Generate Runner 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 sd0xdev/sd0x-harness --skill generate-runner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-runner, .gemini/skills/generate-runner, .github/skills/generate-runner and .opencode/skills/generate-runner in your project.
What does Generate Runner need to run?
Going by SKILL.md and its folder, Generate Runner needs the command-line tools its instructions call (node and bash). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash(node:*), Bash(chmod:*), Bash(bash:*), Write, AskUserQuestion.
Does Generate Runner 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 Generate Runner 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 Generate Runner use?
Generate Runner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Generate Runner use?
About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 717 tokens, read only when the agent opens those files.
What are the alternatives to Generate Runner?
Skills that share tags, products or a category with Generate Runner: Install Anti-Slop Oxlint Rules (dmmulroy/anti-slop, 5.2k stars), Babysit PR To Pass CI (sgl-project/sglang, 37k stars), Rust Best Practices (farm-fe/farm, 5.6k stars) and Go Pedantry (chromedp/chromedp, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Generate Runner?
sd0xdev (a GitHub user) maintains it in sd0xdev/sd0x-harness, which has 192 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 6, 2026.
Source: sd0xdev/sd0x-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.