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 skills add mifunedev/openharness --skill strategic-proposalgit 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/strategic-proposal)<a href="https://agentmods.dev/skills/mifunedev/openharness/strategic-proposal"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/strategic-proposal.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02254 |
| Opus 5 | $0.00037 | $0.01127 |
| Sonnet 5 | $0.00015 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00225 |
Grade A, and why
strategic-proposal 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Proposal
Spawn 5 specialized expert sub-agents in parallel, each proposing roadmap items from their domain. An Expert AI Council drafts the roadmap, a Strategic Critic challenges it with adversarial backpressure, and the Council finalizes with revisions. The result is published as a pinned GitHub issue.
Core principle: SIGNAL OVER FEATURES. Items require evidence of user demand before entering "Build Now" phase. Infrastructure prerequisites are exempt. The Critic ensures the council isn't inflating signal or sandbagging complexity.
Variant: V2MOM / strategic operating model → wiki plan
Use this variant when the user asks for a council to define a V2MOM, operating model, strategic principles, or a plan to add strategic synthesis to the wiki. Do not force the full roadmap/GitHub-issue publishing flow unless the user explicitly asks for a roadmap update.
- Gather current product truth from README/docs/context/wiki plus live external signal if available.
- Spawn a small lens-diverse council (e.g. Product/Founder, Systems/Ops, Market/Docs) rather than the roadmap-specific five expert roles.
- Run one adversarial Strategy Critic after the council draft. The critic must challenge overreach, weak measures, contradictions, and wiki-scope mistakes.
- Final synthesis should separate:
- Council decision: Vision, Values, Methods, Obstacles, Measures.
- Wiki plan: exact target entry, draft frontmatter/body, verification, and rejected scope.
- Prefer one bounded provisional wiki entry first. Extra positioning/docs-IA entries are premature unless they hold distinct durable facts.
- Keep wiki output as synthesis, not council minutes. Raw/source material belongs under
.oh/knowledge/raw/; the tracked entry stays within the wiki word cap and startsconfidence: provisional. - Add explicit approval gates for contested strategic wording (e.g. tagline, key nouns, whether a constraint is too narrow) before implementing file changes.
Session example and final V2MOM synthesis: references/open-harness-v2mom-council.md.
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 Changed · +2 lines 605ae5ca4fc5
- 8d ago First seen · 216 lines · 75 tokens per session scan A f63079845b49
strategic-proposal is a skill published in the GitHub repository mifunedev/openharness (37 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 2,254 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…
cudf-analytics
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.