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 Benknightdark/neo-skills --skill neo-harness-projectgit clone --depth 1 https://github.com/Benknightdark/neo-skillsWrote 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/benknightdark/neo-skills/neo-harness-project)<a href="https://agentmods.dev/skills/benknightdark/neo-skills/neo-harness-project"><img src="https://agentmods.dev/badge/skills/benknightdark/neo-skills/neo-harness-project/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/benknightdark/neo-skills/neo-harness-project"><img src="https://agentmods.dev/badge/skills/benknightdark/neo-skills/neo-harness-project.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.02564 |
| Opus 5 | $0.00046 | $0.01282 |
| Sonnet 5 | $0.00019 | $0.00513 |
| Haiku 4.5 | $0.00009 | $0.00256 |
Grade A, and why
neo-harness-project 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 6d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Harness Builder
依專案現況建立可閱讀、可驗證、可恢復的工程環境。不得套用固定技術棧或理想架構，也不得建立沒有真實檢查能力的空殼。
邊界
- 本技能盤點並建置整個專案的 Harness。
- 需求只涉及
AGENTS.md時，改用neo-harness。 - 目標專案的 Harness 資產必須集中在根目錄
.neo_harness/；唯一例外是必須留在根目錄的AGENTS.md。 - 技能套件自身的
references/、assets/與evals/是技能實作資源，不屬於目標專案的 Harness 產出位置。 - 不得新增使用者未要求的第三方依賴、服務、部署或外部連線。
- 技能內容與產出必須保持供應商中立，不得提及任何特定模型供應商、產品、套件族、官方網址或供應商專屬中繼資料。
- 若無法在遵守中立要求的前提下準確記錄必要專案事實，停止相關產出並回報衝突；不得刪減或改寫事實以規避衝突。
Harness 資產位置規範
下列路徑均以目標專案根目錄為基準：
| 資產 | 正式路徑 |
|---|---|
| 專案入口與工作規則 | AGENTS.md |
| 架構文件 | .neo_harness/ARCHITECTURE.md |
| 計畫規範 | .neo_harness/PLANS.md |
| 專案命令清單 | .neo_harness/docs/scripts.md |
| 進行中的執行計畫 | .neo_harness/docs/exec-plans/active/ |
| 已完成的執行計畫 | .neo_harness/docs/exec-plans/completed/ |
- 不得建立
.neo_harness/AGENTS.md；根目錄AGENTS.md是唯一的 Agent 入口。 - 所有其他 Harness 核心或條件式資產都必須放在
.neo_harness/內，並由根目錄AGENTS.md或相關文件連結。 .neo_harness/是正式且應納入版本控制的專案資產；若被.gitignore或其他忽略規則排除，先標記為blocked，不得自行修改忽略規則。- 不得把非 Harness 文件、既有專案文件或技能套件自身的資源移入
.neo_harness/。
既有舊路徑的搬遷
若盤點發現下列舊路徑存在，必須先提供搬遷預覽並取得使用者對精確清單的明確確認：
| 舊路徑 | 正式路徑 |
|---|---|
ARCHITECTURE.md |
.neo_harness/ARCHITECTURE.md |
PLANS.md |
.neo_harness/PLANS.md |
docs/scripts.md |
.neo_harness/docs/scripts.md |
docs/exec-plans/ |
.neo_harness/docs/exec-plans/ |
- 搬遷預覽必須列出來源、目的地、受影響的連結或索引、驗證命令與復原方式。
- 目的地已存在、來源與目的地內容衝突，或目的地受忽略規則排除時，動作標記為
blocked；不得覆寫、刪除、建立重複副本或建立符號連結。 - 未經確認不得搬遷、批次改名或刪除舊路徑；確認後才可更新受影響的 Harness 連結，並保留可從版本控制或已報告快照復原的依據。
- 不屬於上述清單的舊文件不自動搬遷，除非使用者另行確認。
必要流程
1. 盤點，不寫入
先讀取專案規範、版本控制狀態、根目錄、套件與建置設定、測試、CI、文件、主要入口及現有 Harness 資產，包括 .neo_harness/ 正式路徑與上述舊路徑的既有檔案。命令必須來自可驗證的設定或文件，不得依技術棧猜測。
盤點時必須閱讀 專案評估模型，依來源證據判定成熟度與缺口。未知資訊標為「未知」，不得補成理想狀態。
2. 選擇產出
閱讀 資產選擇矩陣，將候選路徑分類為：
create：路徑不存在，且已有足夠證據建立。update：保留有效內容並補齊缺口。rebuild：現有內容與已確認目標衝突，需重建。migrate：舊 Harness 路徑存在，需依確認結果搬到.neo_harness/並更新受影響連結。skip：沒有需求或證據，不建立。blocked：缺少關鍵事實或違反中立要求。
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/AGENTS.md.template 1.1 KB
- assets/templates/ARCHITECTURE.md.template 630 B
- assets/templates/exec-plan.md.template 823 B
- assets/templates/PLANS.md.template 995 B
- assets/templates/scripts.md.template 36 B
- evals/eval_queries.json 994 B
- evals/evals.json 5.6 KB
- references/artifact-selection.md 5.2 KB
- references/generation-validation.md 5.7 KB
- references/project-assessment.md 2.8 KB
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.
- 6d ago Changed · +41 lines · +10 tokens per session fbdff12d1bd9
- 8d ago Changed · +7 lines 6ee116cdd145
- 12d ago First seen · 81 lines · 83 tokens per session scan A 84cfc91a01d6
neo-harness-project is a skill published in the GitHub repository Benknightdark/neo-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 2,564 once invoked, about $0.0005 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 skills, from other repositories
html-portal-generator
Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.
api-designer
Design RESTful APIs with best practices for consistency and usability.
test-writer
Write thorough tests following TDD and BDD principles.
coding-assistant
Provides coding assistance with best practices and code review.
debug-helper
Systematic debugging approach for identifying and fixing issues.
git-workflow
Git best practices for version control and collaboration.