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 prompt-minergit 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/prompt-miner)<a href="https://agentmods.dev/skills/mifunedev/openharness/prompt-miner"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/prompt-miner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mifunedev/openharness/prompt-miner"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/prompt-miner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 175 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00153 | $0.03020 |
| Opus 5 | $0.00077 | $0.01510 |
| Sonnet 5 | $0.00031 | $0.00604 |
| Haiku 4.5 | $0.00015 | $0.00302 |
Grade A, and why
prompt-miner 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 9d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-miner
Mine the harness's own session history to learn which prompt traits produce the
best sessions, and feed those learnings back into identity. This skill is
the judgment layer on top of the deterministic mine-traces.mjs engine: the
engine collects, scores, and ranks; this skill correlates prompt features against
outcome, mines falsifiable markers, and proposes durable lessons for approval.
It is a cross-session, data-driven cousin of /retro. Where /retro reflects on
the current conversation, /prompt-miner reflects on the corpus of past
sessions across both harnesses.
disable-model-invocation: truesuppresses auto-invocation only — the model will not fire this skill on its own. A user-typed/prompt-minerstill runs the full body below, including the Step-3 LLM marker synthesis. There is no conflict: the deterministic engine produces an objective dataset; the LLM step interprets it.
Privacy contract
This skill reads real session transcripts, which can contain secrets and private content. The contract is non-negotiable:
- Default output is feature vectors + metadata only — never raw prompt text.
The engine omits
promptTextunless--include-prompt-textis passed. --include-prompt-textapplies a redaction pass (line-level token patterns + block-level key bodies) and prints aWARNINGbanner. Use it only when you must read the prompt wording, and never commit the result.- All artifacts land in ephemeral scratch under
$TMPDIR, outside the repo. Never stage, commit, or paste a transcript or an--include-prompt-textreport. - The engine never writes into the repository. Its only outputs are the scratch
artifacts under
$TMPDIR.
When to use
/prompt-minerinvoked to mine the corpus for prompt-quality markers.- Periodically (the daily
crons/prompt-miner.mdcron drives the unattended path; this skill is the interactive path).
When NOT to use
/retro— reflects on the current conversation, not the historical corpus. Use/retroto close a session; use/prompt-minerto learn across sessions./audit context//audit skills//wiki lint— those score harness artifacts (context budget, skills, wiki)./prompt-minerscores prompts.
What ships with it
8 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.
- references/markers.md 4.3 KB
- references/pi-parity.md 1.3 KB
- references/report-schema.md 5.4 KB
- references/scoring.md 7.1 KB
- scripts/__tests__/fixtures/claude-sample.jsonl 2.6 KB
- scripts/__tests__/fixtures/pi-sample.jsonl 1.2 KB
- scripts/__tests__/mine-traces.test.mjs 24 KB runs code
- scripts/mine-traces.mjs 33 KB runs code
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.
- 9d ago First seen · 228 lines · 153 tokens per session scan A 096b190fb352
prompt-miner is a skill published in the GitHub repository mifunedev/openharness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 153 tokens to every session and 3,020 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…
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.