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 agentmods add commands/jabrena/plinth/explore-designgit clone --depth 1 https://github.com/jabrena/plinthWhat 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 | $0.00015 | $0.00936 |
| Opus 5 | $0.00008 | $0.00468 |
| Sonnet 5 | $0.00003 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
explore-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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
explore-design
Improve and refine the technical approach for an issue or OpenSpec change after initial specification—with alternatives, trade-offs, compatibility review, rollout controls, and verification strategy—before implementation.
Usage
/explore-design <issue|openspec-change>
Accepted Inputs
- Issue or user story
- OpenSpec change with unresolved technical approaches or design gaps
- Existing architecture context and constraints
- Relevant requirements, ADRs, or technical notes linked to the issue or change
Owning Agent
@plinth-architect
Associated Skills
051-design-two-steps-methodsfor every refinement so preparatory work, behavior change, and verification remain explicitly sequenced052-design-hamburger-methodwhen the scope is broad enough to need smallest-useful vertical slices053-design-simple-ruleswhen alternatives need ordered design tradeoff evaluation before finalizing the direction054-design-tddwhen testing-related requirements need test-first sequencing and verification-driven refinement055-design-parallel-changewhen database migration requirements need expand, migrate, contract sequencing056-design-avoid-breaking-changeswhen compatibility surfaces may change during refinement057-design-feature-toggleswhen rollout, rollback, compatibility windows, or temporary behavior controls affect the design direction059-design-atddas the final alignment gate when an OpenSpec change provides a proposal, specification scenarios, and a task checklist121-java-object-oriented-design, then122-java-type-design, then123-java-design-patternswhen Java responsibilities, type boundaries, or collaboration decisions affect the refined approach130-java-testing-strategieswhen testing strategy, boundary coverage, flakiness, or verification quality affect the refined approach
Workflow position
Runs after /create-spec, not as the first mission in the workflow.
Workflow
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.
- 3d ago First seen · 81 lines · 15 tokens per session scan A d4bbd399bc76
explore-design is a command published in the GitHub repository jabrena/plinth (435 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 936 once invoked, about $0.0001 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 commands, from other repositories
ai-do
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.