impl

An autonomous implementation workflow that turns a product requirements document into development tasks and carries out the work across sessions. A PRD is a document describing what should be built and its requirements.

In plain words
What is it for?
Use it to break a PRD into tasks, execute those tasks in a loop, resume from saved work, and escalate when progress is blocked.
Why use it?
It keeps implementation work organised and preserves progress when a project spans multiple sessions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jazz1x/harnish/impl
Any agent
npx skills add jazz1x/harnish --skill impl
Clone the repo
git clone --depth 1 https://github.com/jazz1x/harnish

Made for: Claude Code, Codex.

Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00180 $0.04066
Opus 5 $0.00090 $0.02033
Sonnet 5 $0.00036 $0.00813
Haiku 4.5 $0.00018 $0.00407

Measured 2d ago against content hash d5287c9a8166, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl 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 2d 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.

skills/impl/SKILL.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

impl — Autonomous Implementation Engine (the "harnish" engine)

Do not judge. Follow the rules. When lost, return to harnish-current-work.json. When stuck, escalate. No invention.

Skill Chain

drafti-architect (or drafti-feature) → impl → galmuri:ralphi (sibling plugin)
Skill Standalone Call Prerequisites
drafti-architect Yes None (only needs a technical problem)
drafti-feature Yes Requires a planning document
impl Yes docs/prd-*.md or existing harnish-current-work.json
galmuri:ralphi Yes (external) Specify target files/directories to verify

When harnish starts without a PRD: "No PRD found. Please create one first with /drafti-architect or /drafti-feature."

Bash Convention

bash 3.2+, python3 (3.14+). macOS/Linux. No jq required as of v0.1.0.

Each Bash tool invocation is a fresh subshell — variables do not survive across calls. Every bash block in this skill must re-declare HARNISH_ROOT="${CLAUDE_PLUGIN_ROOT}" inline before using any script path. There are no persistent script-name aliases; full paths ($HARNISH_ROOT/scripts/{name}.sh) are used directly.

State counters (TASK_COMPLETE_COUNT, etc.) are tracked by the LLM in conversation memory, not in shell variables. COMPRESS_EVERY_N = 5.

Entry Check

If invoked with no context (no PRD path, no task description, no experience command, no harnish-current-work.json in CWD): → Ask: "무엇을 구현할까요? PRD 파일 경로나 작업 내용을 알려주세요." → Wait for user response before proceeding to Step 1.

Step 1: Mode Detection

Condition Mode Next References to Load
PRD provided, no harnish-current-work.json Seeding Step 2 task-schema.md + progress-template.md
harnish-current-work.json exists Implementation Loop Step 3 escalation-protocol.md + guardrail-levels.md
"자산 현황/압축/기억해/스킬로" Experience Step 5 thresholds.md
harnish-current-work.json exists + session start Restore Step 4

Read the full file on GitHub · 353 lines

Changes

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.

  1. 2d ago First seen · 353 lines · 180 tokens per session scan A d5287c9a8166

Subscribe to this mod's changes

impl is a skill published in the GitHub repository jazz1x/harnish (4 stars, last pushed 3mo ago), licensed MIT. It adds 180 tokens to every session and 4,066 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

migrating-langchain-to-pydantic-ai

Migrate Python LangChain or LangGraph applications to Pydantic AI. Use for LangChain agents, chains, LCEL, or direct LangGraph graphs, persistence, interrupts, and streaming. Do not use for migrations centered on createdeepagent or Deep Agents harness features.

pydantic/pydantic-ai · 69 tokens

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

remote-claude-code

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…

Prism-Shadow/penguin-harness · 107 tokens

penguin-harness-dev

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…

Prism-Shadow/penguin-harness · 119 tokens