Borrowing it
Nothing to install: this file belongs to wquguru/harness-books. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wquguru/harness-books/main/.codex/skills/harness-book-best-practice/SKILL.mdgit clone --depth 1 https://github.com/wquguru/harness-booksWrote 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/wquguru/harness-books/harness-book-best-practice)<a href="https://agentmods.dev/skills/wquguru/harness-books/harness-book-best-practice"><img src="https://agentmods.dev/badge/skills/wquguru/harness-books/harness-book-best-practice/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/wquguru/harness-books/harness-book-best-practice"><img src="https://agentmods.dev/badge/skills/wquguru/harness-books/harness-book-best-practice.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 | $0.00086 | $0.03897 |
| Opus 5 | $0.00043 | $0.01948 |
| Sonnet 5 | $0.00017 | $0.00779 |
| Haiku 4.5 | $0.00009 | $0.00390 |
Grade A, and why
harness-book-best-practice 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 13d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
2 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.
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.
- 13d ago First seen · 274 lines · 86 tokens per session scan A 267b4e431073
harness-book-best-practice is a skill published in the GitHub repository wquguru/harness-books (3,083 stars, last pushed 4mo ago), with no licence file. It adds 86 tokens to every session and 3,897 once invoked, about $0.0004 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
learn-content
Ingest URLs, articles, or text from any source into structured knowledge cards. Stores source URL + metadata + briefing (NOT full text). On-demand retrieval from source. TRIGGER: "learn this", "save this article", "read and remember", "ingest this". NOT FOR: deep-research, summarize, persist use cases.
evaluate
Evaluate requirements, feature requests, and task intake against project DDD context. Produces a GO/DEFER/REJECT/ESCALATE recommendation with ROI scoring, scope definition, and acceptance criteria. TRIGGER: "evaluate this request", "should we build this", "assess this requirement", "triage this". NOT FOR…
persist
Persist knowledge to the correct destination — routes to DDD docs (PRODUCT/TECH/IMPROVEMENT/PROJECT), MEMORY.md, Knowledge/Library/ (searchable store), or EVOLUTION.md based on content type. Unified routing for both manual saves and auto hooks. TRIGGER: "remember", "save", "persist", "沉淀", "record this", "save to…
radar-todo
Manage SwarmAI ToDos — add, list, edit, complete, and delete items that appear in the left-nav ToDo card/overlay. Each todo is a self-contained work packet: when dragged into a chat tab, the agent has all context to start executing immediately. Also proactively creates todos from detected action items and blockers.…
deep-research
Thorough multi-source research with citations, analysis, and synthesis. TRIGGER: "research", "deep dive", "investigate", "find out about". NOT FOR: github-research, consulting-report use cases.
slack
Send, read, search, and manage Slack messages, channels, and reactions via Slack MCP server or API. TRIGGER: "slack", "send slack message", "check slack", "slack channel", "slack DM", "post to slack". DO NOT USE: for email (use Outlook Assistant), Discord, or Teams messages.