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 vidhunnan/agentic-skills --skill exploration-loggit clone --depth 1 https://github.com/vidhunnan/agentic-skillsWrote 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/vidhunnan/agentic-skills/exploration-log)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/exploration-log"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/exploration-log/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/vidhunnan/agentic-skills/exploration-log"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/exploration-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00126 | $0.02483 |
| Opus 5 | $0.00063 | $0.01241 |
| Sonnet 5 | $0.00025 | $0.00497 |
| Haiku 4.5 | $0.00013 | $0.00248 |
Grade A, and why
exploration-log 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exploration-log
Writes the tier no design tool has: a durable record of what was tried and killed, and why.
The failure it prevents is specific. You run four passes at a layout, keep the fourth, delete the other three. Six months later someone proposes direction two again — and nobody can say whether it was already tried or why it lost, so it gets tried again at full cost. Meanwhile the surviving design carries details that were load-bearing decisions in round two and read as invisible leftovers by round five.
Git solves this for code by accident: the rejected approach stays in the history whether you wanted it or not. Design has no equivalent. The alternative is deleted from the file and gone.
Three rules govern this skill:
- Append-only. A killed direction is never deleted. That record is the tier. Prior rounds are frozen; new rounds are appended.
- Never invent what a round taught. Asked what an iteration proved, a model
will supply a plausible design insight. Most rounds genuinely teach nothing
crisp, and
*(nothing conclusive)*is a real, useful answer. - It has to be cheap. Four questions. A log costing ten minutes a round stops after round two, and a tier nobody writes into is worse than no tier.
Instructions
Step 0 — Detect your surface
Using Bash availability:
- Claude Code — Bash works and there's a real filesystem. Full flow, including retrieval against prior rounds.
- Claude.ai — no filesystem. Run the interview and emit the entry as a downloadable artifact. Say plainly that retrieval is unavailable — you cannot answer "have we tried this?" without the log. Don't guess at it.
Step 1 — Resolve the explorations path (Claude Code)
In descending authority:
- A path declared in a CLAUDE.md protocol block —
skill:design-setup's routing table row for Explorations. - An existing folder —
design/explorations/,explorations/,iterations/,rounds/. Match case-insensitively. - Canon —
design/explorations/.
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.
- 9d ago First seen · 203 lines · 126 tokens per session scan A 151c00726341
exploration-log is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 2,483 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.