design-interaction

A method for designing how people use a command-line tool, web interface, or API, including feedback and error recovery. It treats every route to a goal as a complete flow, not just the successful case.

In plain words
What is it for?
Use it to define user goals, success and failure flows, progress feedback, actionable error messages, and accessibility requirements for an interface.
Why use it?
Users need to know whether an action was received, is still running, succeeded, or failed. Designing prevention, detection, and recovery makes errors understandable and fixable.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nullhack/temple8/design-interaction
Any agent
npx skills add nullhack/temple8 --skill design-interaction
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00396
Opus 5 $0.00020 $0.00198
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured 2d ago against content hash 1743ee9175b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-interaction 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 2d 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.

.opencode/skills/design-interaction/SKILL.md · 15 lines

What it actually says

Design Interaction

  1. Load [[design/interaction-design]], [[design/accessibility]] — the conversation model, the two gulfs, feedback + error design, and the accessibility floors that apply to every interaction.
  2. Identify the surface (CLI / HTTP API / web UI) and load its surface-specific knowledge: [[design/cli-design]] for a terminal, [[design/api-design]] for an HTTP service, [[design/visual-design]] for a graphical surface.
  3. State the user's goal for the surface in one sentence, then list the flows that reach it — including the recovery path from each error. A flow is a contract, not a happy path; the error paths are designed here, not deferred.
  4. Design the feedback for every action: received, in progress, succeeded, failed — within a latency the user can associate with the action. Close the gulfs of execution (signified affordances, the user's vocabulary, one primary action) and evaluation (legible state, results in the user's terms).
  5. Design the errors along prevent → detect → recover: constrain input to prevent; validate early to detect; write an actionable, in-the-user's-terms message with a fix path to recover. Never ship a flow whose error paths have not been designed.
  6. Verify the accessibility floor: keyboard reachability + visible focus (graphical), contrast per WCAG 2.2, color never the sole signal, semantic markup. IF a flow fails the floor THEN fix the design before handoff.
  7. Document the interaction contract: the flows, the feedback at each step, and the error catalog. Hand to the implementer; the contract, not a Figma file, is the source.
Changes

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.

  1. 2d ago First seen · 15 lines · 41 tokens per session scan A 1743ee9175b6

Subscribe to this mod's changes

design-interaction is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 41 tokens to every session and 396 once invoked, about $0.0002 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.