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/specnpx skills add mifunedev/openharness --skill specgit 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 | $0.00190 | $0.01629 |
| Opus 5 | $0.00095 | $0.00814 |
| Sonnet 5 | $0.00038 | $0.00326 |
| Haiku 4.5 | $0.00019 | $0.00163 |
Grade A, and why
spec 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec — canonical workflow dispatcher
/spec <subcommand> [args] is the single entry point to the decomposed
spec-* workflow nodes. The first whitespace-delimited token of $ARGUMENTS
selects the subcommand; everything after it 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.
This is the only spec pipeline; there is no all-in-one composer beside it.
references/execute.md holds the build mechanics in full — the issue, the branch,
the draft PR, the build launch, the /eval and wiki gates, the promotable
classification, and the undraft — so learning what the build does never sends a
reader to a second skill. The dispatcher splits the pipeline so each node can be
run independently or fanned out at scale via /delegate.
Workflow contract
The canonical operative path is
spec-plan → spec-execute → merge → reset|clean.
There is no automated selection node. A human selects the work and approves
prd.md; that approval is the commitment gate. /spec execute runs
build ⇄ audit → evidence → spec-retro → improve and stops at a ready-for-review
pull request. The human alone merges. The runner performs reset or clean.
The .oh/tasks/<slug>/ folder is the interface between all three subcommands.
evidence.md records plan requirements, build results, reasons for divergence,
and unverified work. /spec execute refuses to mark a pull request ready when that
evidence is absent or uncommitted.
Subcommands
| Subcommand | Arg shape | Purpose | Procedure |
|---|---|---|---|
plan |
<topic> [--plan <path>] [--issue <N>] [--slug <slug>] [--prefix <type>] [--repo <o/n>] [--base <branch>] |
Turn a topic/plan/issue into a fully-scaffolded .oh/tasks/<slug>/ four-file folder |
references/plan.md |
execute |
<slug> [--pr <N>] [--repo <o/n>] [--remote <name>] [--base <branch>] |
implementation ⇄ audit → evidence → spec-retro → improve to a ready PR, stopping at the human merge gate |
references/execute.md |
retro |
<slug> [--dry-run] |
Execution-side /retro scoped to a built .oh/tasks/<slug>/ |
references/retro.md |
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 · 112 lines · 190 tokens per session scan A a31eb1ec1fe3
spec is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 190 tokens to every session and 1,629 once invoked, about $0.0010 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.