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/releasenpx skills add mifunedev/openharness --skill releasegit 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 | $0.00053 | $0.01301 |
| Opus 5 | $0.00026 | $0.00651 |
| Sonnet 5 | $0.00011 | $0.00260 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
.github/workflows/release.yml owns version allocation and artifact mutation.
The workflow validates every push to main or master first, then reserves the
v<version> tag for the version root package.json names, publishes GHCR and
the CLI (or confirms the CLI version already exists), and finally publishes the
GitHub Release. Do not pre-create a release tag, draft, or release/<version>
branch.
Root package.json holds the version. No other file records it. A release is a
deliberate bump: an unchanged version gives a clean, green no-op run.
1. Resolve the canonical destination
if git remote get-url upstream >/dev/null 2>&1; then
REMOTE=upstream
else
REMOTE=origin
fi
REPO=$(gh repo view "$(git remote get-url "$REMOTE")" --json nameWithOwner -q .nameWithOwner)
if git ls-remote --exit-code --heads "$REMOTE" main >/dev/null 2>&1; then
TARGET=main
elif git ls-remote --exit-code --heads "$REMOTE" master >/dev/null 2>&1; then
TARGET=master
else
echo "No main or master release branch exists on $REMOTE" >&2
exit 1
fi
SOURCE=$(git branch --show-current)
printf 'Repo: %s · source: %s · release branch: %s\n' "$REPO" "$SOURCE" "$TARGET"
2. Pre-flight
Require all of the following before a release push:
- The working tree is clean.
- The source commit is pushed to the canonical remote.
- CI for the source commit is green.
- Root
package.jsonnames the version to publish, and nov<version>tag exists yet. An unbumped push is a green no-op that publishes nothing. CHANGELOG.mdhas a## [<version>]section matching that version (the workflow falls back to[Unreleased]when the section is absent).- The remote release branch is an ancestor of the source commit, so promotion is a fast-forward.
test -z "$(git status --porcelain)" || { echo "Working tree is dirty" >&2; exit 1; }
git fetch "$REMOTE" "$SOURCE" "$TARGET" --tags
VERSION=$(node -p "require('./package.json').version")
git rev-parse -q --verify "refs/tags/v$VERSION" >/dev/null && {
echo "v$VERSION is already tagged; bump package.json to cut a new release" >&2
exit 1
}
grep -q "^## \[$VERSION\]" CHANGELOG.md || {
echo "CHANGELOG.md has no section for $VERSION" >&2
exit 1
}
SHA=$(git rev-parse "$REMOTE/$SOURCE")
test "$(git rev-parse HEAD)" = "$SHA" || {
echo "Local $SOURCE is not identical to $REMOTE/$SOURCE" >&2
exit 1
}
git merge-base --is-ancestor "$REMOTE/$TARGET" "$SHA" || {
echo "$TARGET has diverged from $SOURCE; reconcile before release" >&2
exit 1
}
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 · 130 lines · 53 tokens per session scan A b1223f80d1e5
release is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,301 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
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.