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/nullhack/temple8/design-interactionnpx skills add nullhack/temple8 --skill design-interactiongit clone --depth 1 https://github.com/nullhack/temple8What 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 | $0.00041 | $0.00396 |
| Opus 5 | $0.00020 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
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.
What it actually says
Design Interaction
- Load [[design/interaction-design]], [[design/accessibility]] — the conversation model, the two gulfs, feedback + error design, and the accessibility floors that apply to every interaction.
- 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.
- 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.
- 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).
- 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.
- 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.
- 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.
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.
- 2d ago First seen · 15 lines · 41 tokens per session scan A 1743ee9175b6
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.
Other skills, from other repositories
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
test-generator
Generate pytest test cases for Python functions and classes.
python-binance
Help developers use the python-binance library for trading on Binance. Use when code imports binance, references Client/AsyncClient, or asks about Binance API trading, market data, websockets, or account management.
itx:execute
Execute the plan for an issue (parent or subtask).
clawctl
Know the clawctl CLI and manage your Clawrium fleet (hosts, agents, providers, channels, integrations, skills, secrets).
create-playwright
Record a browser-session demo (MP4) using Playwright via a replay-first compile pipeline. A YAML spec drives the driver script, the recording, and the ElevenLabs voiceover — mirrors create-vhs for browser flows.