Claude Code Harness is a development workflow for coding agents that organizes work into planning, implementation, review, synchronization, and release stages. It helps developers keep specifications, tests, independent reviews, and release evidence connected while using tools such as Claude Code, Codex CLI, Cursor, or Grok.
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.
npx skills add Chachamaru127/claude-code-harness --skill japanese-writing-draftergit clone --depth 1 https://github.com/Chachamaru127/claude-code-harnessWrote 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/skills/chachamaru127/claude-code-harness/japanese-writing-drafter)<a href="https://agentmods.dev/skills/chachamaru127/claude-code-harness/japanese-writing-drafter"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/japanese-writing-drafter/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.
<a href="https://agentmods.dev/skills/chachamaru127/claude-code-harness/japanese-writing-drafter"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/japanese-writing-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00208 | $0.02135 |
| Opus 5 | $0.00104 | $0.01068 |
| Sonnet 5 | $0.00042 | $0.00427 |
| Haiku 4.5 | $0.00021 | $0.00214 |
Grade A, and why
japanese-writing-drafter 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
japanese-writing-drafter
会話内で operator が agent の日本語表現を直したときだけ、その指摘を pending の writing-rule 提案として ~/.claude/writing-lint/proposals.jsonl に追記する。提案の追記のみを行い、承認・却下・rules.jsonl への昇格は一切行わない。
核心契約
- 書き込みはこの skill 経由のみ:
proposals.jsonlに status: pending の行を追記できるのはこの skill だけ。他のどのスクリプト・hook もこのファイルに書き込まない。 - 自動昇格経路は存在しない:
rules.jsonlを更新できるのは人間が手で実行するscripts/writing-rule-approve.sh --id <id>だけ。この skill からも、他のどの hook からもwriting-rule-approve.shを自動起動しない。 - 1 回の検知につき 1 提案。status は常に
"pending"で書く。
トリガー条件
会話の中で、次のいずれかが起きたときだけ発動する(雑談・通常の作業指示では発動しない)。
- operator が直前の agent 発言・生成物の日本語表現をそのまま書き直した
- operator が「その言い方はNG」「〜じゃなくて…と書いて」のように文体・言い回しを名指しで指摘した
- operator が明示的に「これルール化して」「writing-lint に登録して」と言った
手順
- before / after を確定する: 直された元の表現 (before) と、operator が示した / 暗に求めた書き直し後の表現 (after) を会話から抽出する。before が具体的な語句・言い回しに絞れないほど曖昧なら、提案せずに終える(無理に一般化しない)。
- pattern を作る: before の該当フラグメントを Go 正規表現 (RE2) として書く。特殊文字はエスケープする。ヒット範囲を広げすぎない(
writing-rule.v1のpatternは文全体ではなく該当箇所のみでよい)。 - good を作る: after をそのまま、または要点を保った短い言い換えとして書く。
- scenes を決める: 会話の文脈から分かるときだけ
["external"]/["chat"]/["docs"]等を付ける。不明なら省略する(省略は「全シーン適用」の意味になる。無理に推測しない)。 - id を作る: 内容が分かる kebab-case スラッグに 8 桁の一意サフィックスを付ける(例:
no-meta-narration-a1b2c3d4)。 - 追記する: 以下のコマンドで
templates/schemas/writing-rule-proposal.v1.jsonに対する手書きバリデーション(必須キー +additionalProperties: false)を通してから 1 行追記する。CLAUDE_WRITING_LINT_PROPOSALSが設定されていればそのパスを、無ければ~/.claude/writing-lint/proposals.jsonlを使う。
python3 - <<'PY'
import json, os, sys, uuid
from datetime import datetime, timezone
repo_root = "REPO_ROOT" # 呼び出し時に実際のリポジトリルートへ置き換える
schema_path = os.path.join(repo_root, "templates/schemas/writing-rule-proposal.v1.json")
proposals_path = os.environ.get("CLAUDE_WRITING_LINT_PROPOSALS") or os.path.join(
os.path.expanduser("~"), ".claude/writing-lint/proposals.jsonl"
)
with open(schema_path, encoding="utf-8") as f:
schema = json.load(f)
record = {
"id": "SLUG-" + uuid.uuid4().hex[:8],
"pattern": "PATTERN_HERE",
"good": "GOOD_HERE",
"status": "pending",
"evidence": "EVIDENCE_HERE",
"created_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
}
# scenes / severity は分かるときだけ足す:
# record["scenes"] = ["external"]
# record["severity"] = "warning"
def validate(data, sch):
required = set(sch.get("required", []))
props = sch.get("properties", {})
if sch.get("additionalProperties") is False:
extra = set(data.keys()) - set(props.keys())
if extra:
raise ValueError(f"additional properties not allowed: {sorted(extra)}")
for key in required:
if key not in data:
raise ValueError(f"missing required property: {key}")
validate(record, schema)
os.makedirs(os.path.dirname(proposals_path) or ".", exist_ok=True)
with open(proposals_path, "a", encoding="utf-8") as f:
f.write(json.dumps(record, ensure_ascii=False) + "\n")
print(f"drafted pending proposal: {record['id']}")
PY
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.
- 11d ago First seen · 94 lines · 208 tokens per session scan A 2ce6feea0e78
japanese-writing-drafter is a skill published in the GitHub repository Chachamaru127/claude-code-harness (3,109 stars, last pushed 4d ago), licensed MIT. It adds 208 tokens to every session and 2,135 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…