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 skills/outlinedriven/odin-codex-plugin/design-an-interfacenpx skills add OutlineDriven/odin-codex-plugin --skill design-an-interfacegit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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/outlinedriven/odin-codex-plugin/design-an-interface)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/design-an-interface"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/design-an-interface.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00996 |
| Opus 5 | $0.00031 | $0.00498 |
| Sonnet 5 | $0.00012 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
design-an-interface 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- design-an-interface — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply "Design It Twice" (Ousterhout, A Philosophy of Software Design): the first interface is rarely the best. Generate at least three radically different shapes for the same module, then compare on depth and ease of correct use. Implementation is out of scope — this skill stops at the contract.
Run discovery before generation. When the module already has callers, dispatch an Explore agent to enumerate them (fd for files, git grep/ast-grep for usage sites) so the constraint set reflects real consumers, not imagined ones.
Modality vs adjacent skills: This is divergent generation under enforced contrast. Implementation planning is convergent and execution-oriented. Clarifying-question protocol is VS-shaped clarification on a single direction. Pick this skill when the answer is "we don't yet know the right shape" and the value is in deliberate contrast across N candidates.
Workflow
1. Frame the contract
Capture, in this order, before any design work:
- The problem the module solves, in one sentence.
- The callers — peer modules, external consumers, tests — and which one is primary.
- The key operations, ranked by frequency.
- Constraints: performance budget, compatibility surface, existing patterns the module must echo.
- The information boundary: what the module hides versus what it must expose.
If any item is unknown, surface it as a question before proceeding. Designing on assumed callers wastes the parallel-generation budget.
2. Generate divergent designs in parallel
Dispatch 3–4 Explore agents simultaneously, each with a distinct constraint that forces divergence. Suggested constraint slate:
- Agent A: minimise the surface — 1–3 entry points maximum.
- Agent B: maximise generality — accept many shapes of input.
- Agent C: optimise for the dominant call site at the cost of the rare one.
- Agent D: borrow shape from a named external paradigm (iterator, builder, capability handle, effect handler).
Each agent returns: contract signature, one realistic call-site example, what the design hides internally, and the trade-offs it accepts.
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.
- 4d ago First seen · 83 lines · 62 tokens per session scan A ba626f659fd1
design-an-interface is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 996 once invoked, about $0.0003 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
triage-issue
Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.