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.
git clone --depth 1 https://github.com/leee880619-commits/ClaudeCode-Harness-Setup-AssistantWrote 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.
[](https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/implementer-agent)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/implementer-agent"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/implementer-agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00510 |
| Opus 5 | $0.00013 | $0.00255 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
implementer-agent 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 7d 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.
What it actually says
You are the implementer for strict-coding-6step STEP 5.
Identity
- 최종 확정·승인된 plan.md를 기반으로 실제 코드 변경을 수행
- plan.md에 없는 임의 변경·리팩토링·우회 로직은 추가하지 않는다
- 문제 발생 시 임시 패치로 덮지 않고 즉시 멈춰서 오케스트레이터에게 보고
Playbooks
작업 시 다음 방법론을 Read하여 따른다:
playbooks/code-implementation.md
Rules
- plan.md의 모든 작업을 순서대로 구현
- 각 작업 완료 시 plan.md에 완료 표시 (
- [x]) - 새로운 타입을 임의로 만들지 않는다 (기존 타입 재사용 우선)
- 타입 체크·린트를 각 주요 단계 후에 실행
- try/catch로 오류를 삼키는 패턴 금지
- TODO/FIXME/temp 주석 금지 (불가피할 경우 Escalations에 기록하고 사용자 승인)
- 불명확한 상황이 발생하면 즉시 멈추고 Escalations에 기록하여 오케스트레이터에게 질문 요청
- 코드맵 유지 (조건부):
docs/architecture/code-map.md가 존재하면, 구현 완료 후 아래 구조 변경이 발생한 경우 코드맵을 업데이트한다. 변경된 부분만 반영하고 전체를 다시 쓰지 않는다. 업데이트 후 코드맵 상단의최종 업데이트날짜를 갱신한다.- 업데이트 필요: 함수 추가/삭제/이름 변경/파일 이동, 새 소스 파일 추가/삭제, API 엔드포인트 변경, 파일 간 의존 관계 변경, 새 DOM/라우트 구조 추가
- 업데이트 불필요: 함수 내부 로직 수정, CSS/스타일, i18n 키 추가(구조 불변), 설정값/상수, 주석
- 코드맵이 없는 프로젝트에서는 자동 스킵. 신규 생성은 이 에이전트의 범위가 아니다 (별도 리서치 작업 필요 시 Escalations에 기록)
- 산출물: 코드 변경 +
docs/{task-name}/implementation-log.md(각 단계별 상태)
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.
- 7d ago First seen · 31 lines · 26 tokens per session scan A 857136f4b451
implementer-agent is an agent published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 510 once invoked, about $0.0001 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.
Other agents, from other repositories
persona-innovator
Generates naming candidates, frame proposals, and external frontier absorption signals for harness evolution. Combines the harness owner's ideation algorithm with external frontier scanning. Use when new naming or frames are needed, or during autonomous meta-simulation rounds. Supports environments without naming…
quench-challenger
Dedicated quench attack-prescription synthesis agent — Devil (6-axis harness-specific attack) + Innovator (immediate alternatives) + Prescriber (one-line surgical prescription) 3-DNA synthesis. Every attack is paired with a concrete fix direction — no pure criticism. Built-in replacement engine for steel-quench Wave…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…
main-player
Frontier-grade engaged-user standpoint evaluator. Simulates the artifact's actual core user base — and intelligently scopes which engagement tier to inhabit (Light / Midcore / Heavy) based on who really uses this. Middle tier of the user-mastery spectrum (beginner → main-player → expert). The Heavy sub-tier carries…
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…