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/interview-generalnpx skills add nullhack/temple8 --skill interview-generalgit 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 | $0.00030 | $0.00366 |
| Opus 5 | $0.00015 | $0.00183 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
interview-general 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
Interview (General)
- Load [[requirements/interview-techniques]], [[methodology/simplicity-discipline]] — CIT, Laddering, CI Perspective Change, the Funnel, the Active Listening protocol, and the simplicity discipline that runs alongside every funnel level.
- Bootstrap the interview-notes. IF
.cache/<session_id>/interview-notes.mddoes not exist THEN render it from.templates/cache/interview-notes.md.template(substitute<session_id>). The skeleton carries the funnel level headers only; absence on a first pass is expected — never a deliberation point. IF it exists THEN it carries the prior cycle's summarized interview (a ~1000-word summary left byrefresh-cycle) — read it for continuity and append the general findings beneath the Level 1 header. - Ask seven big-picture questions in any natural order: Who, What, Why, When/Where, Success, Failure, Out-of-scope. Do not introduce category or topic labels — let the stakeholder's own categories emerge first (priming bias).
- Probe every answer with CIT (a concrete past incident) and Laddering (climb to a writable constraint). IF recall stalls THEN re-frame from another actor's seat (CI Perspective Change).
- Ask the simplicity question: "What's the smallest surface that meets the need?" The stakeholder's answer names the minimum the contracts must honour; an answer that inflates scope beyond the cited need is a speculative structure, flagged here per [[methodology/simplicity-discipline]].
- Apply Active Listening L1: paraphrase each answer before the next question.
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 · 14 lines · 30 tokens per session scan A c953596c700f
interview-general is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 30 tokens to every session and 366 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.