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/harness-contextnpx skills add mifunedev/openharness --skill harness-contextgit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/mifunedev/openharness/harness-context)<a href="https://agentmods.dev/skills/mifunedev/openharness/harness-context"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/harness-context.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 | $0.00073 | $0.00959 |
| Opus 5 | $0.00036 | $0.00479 |
| Sonnet 5 | $0.00015 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
harness-context 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Context
Use this skill when the user asks about Open Harness layout, lifecycle, conventions, git workflow, or where files live.
Steps
- Read
CLAUDE.mdfor the orchestrator contract — what the root-level agent does and does not do. - For layout questions, read the per-directory
README.mdfiles (e.g..oh/README.md,.oh/tasks/README.md,.oh/scripts/README.md) plus the nested agent guides.worktrees/AGENTS.md,projects/AGENTS.md, andcrons/AGENTS.md, and theHow the system fits togethersection ofAGENTS.md. There is no single comprehensive tree — use the filesystem and the directory READMEs. - For behavioral norms, now collapsed from an always-on tier into on-demand
skills, the canonical homes are:
/git(.oh/skills/git/SKILL.md) — issue / branch / commit / PR conventions/t3(.oh/skills/t3/references/sandbox-processes.md) — tmux sessions for long-running processesreferences/directory-readme.md— when a directory needs a README/delegate(.oh/skills/delegate/SKILL.md) — wave decomposition and the recursion budget for sub-agents
- For skill-listing or skill-source-of-truth questions, load
references/skill-source-of-truth.mdand separate the tracked Open Harness shared skill library (.oh/skills/*/SKILL.md, exposed through.claude/skills,.codex/skills,.pi/skills, and Hermes' runtime.hermes/skills/openharnesssymlink) from the active Hermes runtime catalog (.hermes/skills/plus bundled/profile skills). Do not presenthermes skills listas the repo source of truth without this distinction. - For shared-skill path migrations or cross-agent skill wiring, load
references/shared-skills-symlink-migration.md; update symlinks, runtime boot setup, docs, CI path filters, cron invocations, exact-path eval probes, and fixed-depth support scripts together before declaring the migration done. - For optional sandbox agent/runtime integrations, audit the full runtime/config/auth surface together: compose mounts and env, entrypoint setup/migration, default config seeding, banner sentinels,
.gitignore, docs/wiki/changelog, and compose config validation. If Hermes is involved, loadreferences/hermes-state-auth-split.mdfor the established single-device project-local runtime (config + auth + sessions all under oneHERMES_HOME) + shared-skill symlink pattern, and why auth must not be a cross-device symlink. - For user-facing optional-runtime warnings, update the user-facing runtime docs/README when the fix is likely to recur. Example: Hermes gateway Slack warnings are covered in
references/hermes-gateway-slack.md; document that Hermes' Slack gateway is separate from the Pi Slack extension,hermes-agent[slack]suppliesslack-bolt, Open Harness' installed Hermes uses/usr/local/lib/hermes-agent/venv(so add extras withuv pip install --python /usr/local/lib/hermes-agent/venv/bin/python 'hermes-agent[slack]', notuv tool install), cron still runs without a messaging adapter, and.hermes/README.mdis the right home for Hermes runtime-home/gateway notes rather than the top-level README. Ownership invariant: runtime paths a human uses inside the container should be writable by the defaultsandboxuser; if an image-level install needs root during Docker build, constrain root-owned build paths to that RUN layer and reset runtime env/ownership afterward. - Answer with
path:linecitations.
What ships with it
5 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.
- 6d ago First seen · 46 lines · 73 tokens per session scan A f7c83d12637a
harness-context is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 959 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
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
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.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.