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/herdrnpx skills add mifunedev/openharness --skill herdrgit 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/herdr)<a href="https://agentmods.dev/skills/mifunedev/openharness/herdr"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/herdr.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 | $0.00165 | $0.01780 |
| Opus 5 | $0.00082 | $0.00890 |
| Sonnet 5 | $0.00033 | $0.00356 |
| Haiku 4.5 | $0.00016 | $0.00178 |
Grade A, and why
herdr 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 4d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Herdr CLI
Herdr (herdr, v0.7.4 in this image) is Open Harness's primary interactive
workspace: a server process plus attached clients, with workspaces → tabs →
panes, and agent-state detection per pane. This skill covers driving it from a
non-interactive agent run. Operator-facing setup, persistence volumes, and the
attach story live in docs/integrations/herdr.md — do not duplicate them
here.
Full subcommand catalog: references/command-map.md. Read it when you need a
flag you do not already know; herdr <group> --help is the ground truth and
prints a usage block for every group.
Never do these from an agent run
- Do not run bare
herdr,herdr agent attach, orherdr session attach. They take over the terminal and hijack the operator's client. Useherdr agent read/herdr pane readto observe instead. - Do not run
herdr updateorherdr channel set. Herdr is pinned in the Open Harness image; upgrade by rebuilding against a reviewed release. - Do not run
herdr server stop. It kills every attached client. Only the operator decides that. - Do not read or write
~/.config/herdr/(config.toml, logs,herdr.sock). A.configpath segment is denied to agent tooling repo-wide. Useherdr config checkandherdr status, which report the same facts. - Do not close, kill, or send text to a pane you did not create without the operator asking. Other panes hold live agents mid-task.
Output contract
Socket-API-backed groups (workspace, worktree, tab, pane, agent,
wait, notification, api) print a single JSON line:
{"id":"cli:agent:list","result":{"agents":[...],"type":"agent_list"}}
Pipe them through jq rather than eyeballing — herdr pane list on a busy
workspace is thousands of characters. Plain-text groups are status,
session list, integration status, config check, channel show.
Identifiers:
| Shape | Example | Meaning |
|---|---|---|
w<N> |
w1 |
workspace id |
w<N>:t<HEX> |
w1:t1K |
tab id |
w<N>:p<HEX> |
w1:p1E |
pane id |
term_<hex> |
term_6587653c830dc14 |
terminal id |
What ships with it
1 file 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.
- 4d ago First seen · 165 lines · 165 tokens per session scan A ec9ded0c5a31
herdr is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 165 tokens to every session and 1,780 once invoked, about $0.0008 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.