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 agentmods add skills/mifunedev/openharness/buildernpx skills add mifunedev/openharness --skill buildergit clone --depth 1 https://github.com/mifunedev/openharnessWhat 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 | $0.00068 | $0.00940 |
| Opus 5 | $0.00034 | $0.00470 |
| Sonnet 5 | $0.00014 | $0.00188 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
builder 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder
Build one artifact through the matching type reference. Run inline and inherit the session model; do not fork or override the model unless the artifact being authored has an independently justified need.
Arguments received: $ARGUMENTS
Dispatch
-
Treat the first whitespace-delimited argument as
TYPEand the remainder as the artifact name, request, or path. -
Accept exactly these types:
Type Read and follow agentreferences/agent.mdskillreferences/skill.mdcommandreferences/command.mdrulereferences/rule.md -
If
TYPEis missing or unknown, or the remaining request is empty or only whitespace, print the following and stop without reading type references or modifying files:Usage: /builder <agent|skill|command|rule> <name-or-request> -
Read the selected reference completely, then execute its protocol against the remainder of
$ARGUMENTS. The selected reference is authoritative for artifact shape and type-specific validation.
Shared protocol
Apply these steps for every valid type before the selected reference's type-specific steps.
1. Discover local authority
- Find and read applicable
AGENTS.mdandCLAUDE.mdfiles from repository root through the target directory. More local instructions win; in one directory,AGENTS.mdis canonical. - Identify the source-of-truth artifact directory. In Open Harness and equipped
projects, edit
.oh/agents/or.oh/skills/; provider directories such as.claude/,.codex/, and.pi/are generated or symlinked exposure surfaces. - Outside an Open Harness layout, follow the target project's documented canonical
path rather than creating
.oh/speculatively. - Inspect two or three nearby artifacts of the same type. Reuse their naming, frontmatter, structure, tone, and validation conventions.
- Search for an existing artifact with the same purpose. Prefer a focused update or explicit consolidation over a near-duplicate.
What ships with it
4 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.
- 2d ago First seen · 102 lines · 68 tokens per session scan A d91d81c37001
builder is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 68 tokens to every session and 940 once invoked, about $0.0003 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
langgraph-docs
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an…
skill-generator
Generates AND modifies complete skills from natural language descriptions. Guides the user through need analysis and archetype selection, produces a skill package compliant with the agentskills.io standard, and imports it directly into the user's skills. Also adjusts, enriches or fixes an existing user skill by…
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
cudf-analytics
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.
deepagents-thread-inspector
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…