bowen31337/agent-harness-skills

harness-cli

Drive the `harness` Python CLI — the agent-harness-skills toolkit that generates per-project harness configs, runs quality gates, manages execution plans, boots isolated app instances, and emits structured telemetry. Use whenever the user (or another agent)…

원문 언어: 영어

context-handoff

Context handoff protocol for multi-session agent work. When an agent session ends, write a structured summary to the plan progress log so the next agent can continue seamlessly. The handoff contains search hints — specific file paths, grep patterns, glob…

원문 언어: 영어

dom-snapshot

Browser-free DOM inspection for agents. Fetches or parses server-rendered HTML and returns a compact, structured text snapshot covering headings, ARIA landmarks, navigation, forms, interactive buttons, tables, images, and visible body text — sized to fit…

원문 언어: 영어

error-aggregation

Error aggregation view for agents. Groups recent harness error events by domain and frequency so agents can query the error landscape without parsing raw logs. Pre-computes deduplication, trend detection (rising/falling/stable), and JSON-serialisable…

원문 언어: 영어

harness-resume

Load and present the most recent plan state for agent context handoff. Reads .claude/plan-progress.md (primary) or .plan_progress.jsonl (fallback) and formats the structured plan state — task, status, accomplished work, in-progress items, next steps, and…

원문 언어: 영어

logging-convention

Generates a versioned SPEC.md (or SPEC.json) logging convention document specifying the five required fields every log entry must carry: timestamp, level, domain, trace_id, message. Validates existing NDJSON log files against the convention. Use when…

원문 언어: 영어

perf-hooks

Performance measurement hooks so agents can record and query response times, memory usage (RSS), and startup duration. All measurements are appended to an agent-shared Markdown audit log (docs/exec-plans/perf.md). Timer state survives process boundaries via a…

원문 언어: 영어

harness-screenshot

Screenshot capture skill for recording application state as a visual artifact. Captures browser pages, desktop windows, or terminal output and saves them as timestamped PNG files (or base64-encoded inline artifacts). Use when: (1) documenting the visual state…

원문 언어: 영어

golden-principles-cleanup

Background cleanup task generator for principle violations. Reads .claude/principles.yaml, scans the codebase for violations using the harness principles gate (or text-based fallback), and emits one cleanup task definition per violation cluster into…

원문 언어: 영어

shared-state

Shared agent state publisher and query tool. Agents publish intermediate results (discovered endpoints, schema changes, test results, or arbitrary structured data) into docs/exec-plans/shared-state.yaml so other concurrently-running agents can read them. All…

원문 언어: 영어

env-isolation

Generates environment isolation configuration artefacts for per-worktree agent isolation. Produces .env files, docker-compose service overrides, and shell export scripts that assign each worktree its own port, PostgreSQL schema, SQLite database file, or…

원문 언어: 영어

concurrency-patterns

Scans the codebase for async/await patterns, thread-safety mechanisms, and pool usage, then generates framework-specific concurrency rules and code snippets matched to the detected conventions. Detects: anyio, asyncio (stdlib), threading, concurrent.futures,…

원문 언어: 영어

detect-env-vars

Codebase analysis skill that detects environment variable patterns from .env.example / .env.sample template files, YAML/TOML/JSON/INI config files that use ${VAR} interpolation, and source code references (os.environ, os.getenv, process.env, os.Getenv, ENV[])…

원문 언어: 영어

debt-tracker

Technical debt tracker so agents can log known shortcuts, compromises, or TODOs into docs/exec-plans/debt.md with a severity level and clear remediation notes. Debt items are auto-assigned sequential DEBT-NNN IDs, and the summary table is rebuilt on every…

원문 언어: 영어

boot

Per-worktree boot script generator and instance launcher. Generates a self-contained bash script that starts an isolated application instance on a dedicated port, optionally isolates the database (PostgreSQL schema, SQLite file, or container), and polls a…

원문 언어: 영어

progress-log

Append-only agent progress log for tracking step completion within a plan. Agents call this skill to record timestamped entries as they start, finish, fail, or skip individual steps in an execution plan. All entries accumulate in docs/exec-plans/progress.md…

원문 언어: 영어