菜单
Harness engineering guide — maps all sensors and feedforward guides, teaches self-correction protocol when a CI sensor fires. Use when a sensor fires, before making code changes, or when setting up agent context for a new task. Triggers: "harness", "sensor fire", "CI failure", "self-correction".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate a DORA-REPORT.md for this repository by computing the five core DORA software delivery performance metrics and three DORA agentic metrics from available data sources. Use this when asked to generate a DORA report or assess delivery performance.
Generate a human-friendly overview infographic by scanning the live project structure, including workspace crates, skills, and scripts. Use this skill whenever the user asks to regenerate, refresh, or update the overview diagram. Triggers on phrases like "update the overview", "regenerate the overview SVG", or "sync the overview".
Run comprehensive linting and static analysis on Rust code including clippy, format check, security audit, supply chain, and unused dependencies. Use before committing, during CI, or when reviewing code quality. Triggers: "lint rust", "clippy", "static analysis", "code quality".
Read all open issues (GitHub/GitLab), categorize by type and effort, plan batch implementation order, and coordinate implementation across multiple issues in a single PR/MR. Auto-detects platform from git remote. Use when asked to "implement all issues", "fix all open issues", "batch implement", or "address all issues". Triggers: "all issues", "implement all", "batch issues", "open issues", "fix all", "address all issues".
Automated secret scanning using secretlint to prevent credential leaks.
Compile, test, and verify Rust projects following 2026 best practices. Use when asked to build, compile, or check a Rust project, when CI/CD pipeline needs build steps, or when investigating build failures. Triggers: "build rust", "compile project", "cargo build", "check rust".
| name | harness |
| description | Harness engineering guide — maps all sensors and feedforward guides, teaches self-correction protocol when a CI sensor fires. Use when a sensor fires, before making code changes, or when setting up agent context for a new task. Triggers: "harness", "sensor fire", "CI failure", "self-correction". |
| category | rust |
| license | MIT |
| metadata | {"author":"d-oit","version":"1.0","tags":"harness sensors ci quality self-correction"} |
Agent = Model + Harness. The harness is the system of feedforward guides (what to do before coding) and feedback sensors (what catches violations after coding). It has two axes:
The harness has two modes:
When a computational sensor fires:
cargo fmt, cargo clippy, etc..agents/events/YYYY/MM/DD/ per the metrics-reporter skill.| Sensor | Command | Config | Stage |
|---|---|---|---|
| fmt | cargo fmt --all -- --check | .pre-commit-config.yaml | pre-commit |
| clippy | cargo clippy --all-targets --all-features -- -D warnings | .clippy.toml, .pre-commit-config.yaml | pre-commit + CI |
| deny | cargo deny check | deny.toml | pre-commit + CI |
| nextest | cargo nextest run | Cargo.toml | CI |
| mutants | cargo mutants | [workspace.metadata.cargo-mutants] in Cargo.toml | CI weekly |
| arch_fitness | cargo test --test arch_fitness | tests/arch_fitness.rs | CI |
| insta snapshots | cargo insta review | tests/behaviour_harness.rs | CI |
| gitleaks | gitleaks detect | .gitleaks.toml | CI |
When any sensor fires repeatedly (>2 times in one sprint):
.agents/skills/ using the skill-creator skill.CHANGELOG.md.The steering loop closes the harness: sensors fire → humans and agents update guides → sensors fire less.
HARNESS.md at repo root.scripts/harness-check.sh runs each sensor and emits structured error output with HARNESS VIOLATION prefix.