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/syncnpx skills add mifunedev/openharness --skill syncgit 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 | $0.00231 | $0.01762 |
| Opus 5 | $0.00115 | $0.00881 |
| Sonnet 5 | $0.00046 | $0.00352 |
| Haiku 4.5 | $0.00023 | $0.00176 |
Grade A, and why
sync 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync — bidirectional origin↔upstream sync dispatcher
/sync <subcommand> routes origin↔upstream sync operations. The first
whitespace-delimited token of $ARGUMENTS selects the subcommand; the
remainder is that subcommand's own argument string. Each subcommand's
full procedure lives in a reference doc under references/ — read that
doc and follow it as the authoritative instructions.
The canonical topology (origin=operator fork, upstream=mifunedev
canonical) and the intentional divergences that every sync must preserve
live in references/topology.md. Read it before executing any subcommand.
Subcommands
| Subcommand | Direction | Purpose | Procedure |
|---|---|---|---|
publish |
origin→upstream | Branch off upstream/development, merge-no-commit origin/development, sanitize private state, reconcile structure, eval-gate, draft PR to upstream | references/publish.md |
catchup |
upstream→origin | Cherry-pick the squash commit of a specific upstream feature onto origin/development; never git merge upstream/development |
references/catchup.md |
status |
read-only | Invoke /audit drift and interpret its section (A) framework-drift output to report which direction is needed |
inline — see below |
Dispatch
ARGUMENTS="${ARGUMENTS:-}"
SUB="${ARGUMENTS%% *}" # first token
REST="${ARGUMENTS#"$SUB"}" # everything after it
REST="${REST# }" # trim one leading space
Route on $SUB:
$SUB |
Action |
|---|---|
publish |
Read references/publish.md; execute it with $REST as its argument string. |
catchup |
Read references/catchup.md; execute it with $REST as its argument string. |
status |
Run the status procedure below. |
| anything else (incl. empty) | Print the usage line from argument-hint and stop. Do not guess. |
Status procedure (inline)
The status subcommand is a thin wrapper around /audit drift — it does
NOT reimplement framework drift detection.
- Invoke
/audit driftand capture its full output. - Parse the section (A) summary line (
DRIFT-CHECK (A):or(A) Framework drift: OK):- Origin N behind upstream AND N ahead = 0: report "catchup is available (N commits to port from upstream/development)".
- Origin N ahead of upstream AND N behind = 0: report "publish is available (N commits to push to upstream/development)".
- Both non-zero: report "bidirectional work needed — run
/sync catchupto port upstream features first, then/sync publishto push origin's changes forward." - Both zero: report "in sync — no action needed."
- Print the raw
/audit driftsection (A) output for operator context.
What ships with it
3 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 · 128 lines · 231 tokens per session scan A 724618bdde45
sync is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 231 tokens to every session and 1,762 once invoked, about $0.0012 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.