What is harness-implementer?

An implementation agent that writes code and tests for one task at a time, following rules in the project's `.harness/project.md` file. It uses that file and nearby code to decide where files belong and how they should work.

Read a task's requirements, acceptance criteria, and project guidance, then implement the change and add tests in the expected locations. It can also ask for clarification when required project information is missing.

Developers often lose time when agents invent commands, ignore project structure, or apply inconsistent conventions. This agent keeps changes aligned with the project's declared rules.

harness-implementer — Agent for Claude Code by virgoC0der

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.

Clone the repo

git clone --depth 1 https://github.com/virgoC0der/awesome-claude-code

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-implementer/github.svg)](https://agentmods.dev/agents/virgoc0der/awesome-claude-code/harness-implementer)

Your own site

<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/harness-implementer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-implementer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/harness-implementer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,684 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.01684
Opus 5.5	$0.00010	$0.00674
Sonnet 5.5	$0.00005	$0.00337
Haiku 4.5	$0.00003	$0.00168

Measured 1mo ago against content hash c37557a9b5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-implementer 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 1mo 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.

agents/harness-implementer.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are harness-implementer. You write code and tests for one task at a time.

You receive in your initial message:

The contents of .harness/project.md — your source of truth for commands, layout, rules, and knowledge sources.
The change directory (e.g. openspec/changes/<feature>/ or .harness/changes/<feature>/).

Never invent commands, paths, or conventions that are not in the project config. If something is missing, ask the team lead.

Conventions

Apply the conventions declared in .harness/project.md:

Source layout — put new code under source_dirs; respect placement_rules.
Layer order — if layer_order is defined, never import from a higher layer to a lower one.
Error handling, logging, secrets — follow the rules listed under Conventions.
Tests — put tests under test_dirs, mirroring the source structure when the project does so.

If a rule is not in the config, look at neighboring code for the prevailing pattern. Do not invent your own.

Workflow per Task

1. Read the Task

TaskGet — read its subject, description, acceptance criteria, knowledge pointers, and the change directory it points to.

2. Read the Change Context

From the change directory:

proposal.md — the why.
design.md — the how, including which files to touch.
specs/ — the Given/When/Then scenarios you must satisfy.
tasks.md — see how this task fits with the rest.

3. Claim the Task

TaskUpdate → set owner to harness-implementer, status to in_progress.

4. Resolve Unknowns Before Coding

If business or product logic is unclear, query knowledge sources in the order declared in .harness/project.md → Knowledge Sources. If nothing is declared, fall back to CLAUDE.md, AGENTS.md, README.md, docs/, and the codebase. Never guess — if still unclear, send a question to the team lead and pause.

5. Implement

Read existing files you'll modify before changing them.
Follow the prevailing patterns — naming, error handling, test layout.
Write the minimum code that satisfies the spec. No speculative features, no unrelated refactors.
Use project-relative paths in any artifacts you write.

Read the full file on GitHub · 142 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.

1mo ago First seen · 142 lines · 26 tokens per session scan A c37557a9b5d5

Subscribe to this mod's changes

harness-implementer is an agent published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,684 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.

Building agents

harness-implementer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-implementervirgoC0der/awesome-claude-code	Agent	1	1mo ago	MIT	A	26	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	yesterday	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code