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 JHostalek/dotclaude --skill designgit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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/jhostalek/dotclaude/design)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/design"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/design/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/jhostalek/dotclaude/design"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/design.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 | $0.00013 | $0.00475 |
| Opus 5.5 | $0.00005 | $0.00190 |
| Sonnet 5.5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
design 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 1mo 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.
What it actually says
Explore $ARGUMENTS and produce approaches with distinct core mechanisms. Use the smallest useful set of independent explorers; add one only to cover a material alternative or unresolved gap. If delegation is unavailable, disclose that limit and explore sequentially without claiming independence.
Establish the raw problem, actual constraints, and obvious solutions. Reframe where it exposes a different mechanism; do not force reframing for a bounded problem. Give explorers the same relevant repository context, their chosen method, and a distinct question or provocation. They must not see each other's proposals. Reframings are optional starting points, not constraints. Send revisions back to their authors.
Choose methods that expose different mechanisms; this is a menu, not required coverage:
| Method | Approach and check |
|---|---|
| Build upward | Start with the smallest useful unit; check emergent needs and necessary upfront investment. |
| Work backward | Derive prerequisites from the ideal outcome; check the path is buildable. |
| Constraint first | Solve or dissolve the hardest constraints; preserve the user outcome. |
| Transfer an analogy | Borrow a mechanism from another domain; identify where the analogy breaks. |
| Eliminate | Remove parts while preserving value; account for interactions and useful polish. |
| Adversarial | Design around consequential failures; state the cost of robustness. |
| Compose | Combine proven primitives; account for glue and dependency assumptions. |
| Evolve over time | Show the initial design, observable change triggers, and migration path; avoid speculative infrastructure. |
| Stakeholder trade-offs | Expose conflicting needs and selectable compromises; prioritize rather than satisfy everyone equally. |
Each explorer returns its mechanism, benefits, sacrifices, and conditions for choosing it. Compare mechanisms, merge cosmetic variants, and identify shared assumptions. Reopen exploration only when convergence or an uncovered assumption hides a useful option.
Save docs/designs/<short-name>.md with the problem and useful reframings, a landscape of approaches, their trade-offs and selection conditions, shared assumptions, and consequential unexplored territory. Include diagrams when they explain architectural or spatial choices. Stop after presenting the alternatives; implementation requires the user's selection or authorization.
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.
- 1mo ago Changed · -59 lines · -7 tokens per session d9936ca71e63
- 1mo ago First seen · 88 lines · 20 tokens per session scan A 307a73505387
design is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 3d ago), licensed CC0-1.0. It adds 13 tokens to every session and 475 once invoked, about $0.0001 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
pulser
Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter, conflicts, usage-hooks), classifies skill types, generates prescriptions, and runs eval tests. Use when checking skill quality, auditing…
poteto-mode
Bundled skills live at ../ /SKILL.md from this file, so put this file's absolute path in every poteto-agent prompt.
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
create-formal-verification-skill
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers…
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.