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 petekp/claude-code-setup --skill latent-potentialgit clone --depth 1 https://github.com/petekp/claude-code-setupWrote 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/petekp/claude-code-setup/latent-potential)<a href="https://agentmods.dev/skills/petekp/claude-code-setup/latent-potential"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/latent-potential/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/petekp/claude-code-setup/latent-potential"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/latent-potential.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00191 | $0.03181 |
| Opus 5.5 | $0.00076 | $0.01272 |
| Sonnet 5.5 | $0.00038 | $0.00636 |
| Haiku 4.5 | $0.00019 | $0.00318 |
Grade A, and why
latent-potential 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 6d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Latent Potential
Walk into the project the way a hand-picked expert team would: a strategist, a positioning specialist, a product thinker, an architect, a distribution person, an ecosystem watcher, and a skeptic. The job is not to review the code. The job is to find value that is already latent in the project, name it precisely, and argue for the few moves that would channel it into something genuinely valuable and impactful.
"Latent" is the operative word. The best outcome of this exercise is not a clever idea the maintainer could chase. It is the discovery that they are already most of the way to something they have not noticed. Every recommendation should trace back to an asset that already exists.
Principles
-
Mechanisms, not labels. Describe the project by what it actually does, not by its category. "A note-taking app" invites note-taking-app ideas. "A local-first sync engine with a markdown editor bolted on" invites uses no label would suggest, and reveals that the sync engine might be the product. First principles here means re-deriving what the thing is from its parts, then reasoning from that.
-
Latent means already present. Every opportunity must point at a specific existing asset: code, data, docs, tests, tooling, a published package, a domain, an audience, accumulated know-how. Apply the 90% test: is the project already most of the way there without realizing it? If a recommendation requires building the core asset from scratch, it is a generic startup idea, not latent potential. Cut it or flag it as out of scope.
-
Lateral before vertical. Sweep wide first. Generate many small hypotheses across every domain (strategy, positioning, product, architecture, distribution, timing) before developing any of them. The first good idea is a trap: it anchors every thought after it. Depth comes later, and only for survivors.
-
Evidence or it does not ship. Cite real files, real commits, real docs. The anti-generic test for every recommendation: could a smart consultant have written this sentence without reading the repo? If yes, it does not belong in the report.
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.
- 6d ago Changed d81e45e4534f
- 1mo ago Changed · +191 tokens per session ba996e25736f
- 1mo ago First seen · 156 lines · 0 tokens per session scan A faab96018c53
latent-potential is a skill published in the GitHub repository petekp/claude-code-setup (48 stars, last pushed yesterday), licensed MIT. It adds 191 tokens to every session and 3,181 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
workspaces
How an Open SWE workspace's sandbox image works and how to change it — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about…
linear-tickets
Create or update high-quality Linear tickets while preserving the originating report, diagnostic links, attachments, and reporter/requester attribution. Read this whenever someone asks to create, recreate, or update a Linear issue.
generative-ui
Use when presenting information already in hand as a small, static structured panel in the conversation — status, results, comparisons, or a compact summary — rather than prose, a markdown table, a widget, or an app.
st-widget-builder
Use when the user asks to render, build, visualise, mock up, or show a widget (chart, dashboard, card, table, graph) in the Mewbo Console. Teaches how to delegate the work to the st-widget-builder sub-agent instead of writing HTML or inline code yourself.