interview-building-blocks

An interview step for dividing a software idea into named building blocks with rough boundaries.

In plain words
What is it for?
Use it after gathering requirements to name the main system areas, check whether each is needed, identify gaps, and record the boundaries in interview notes.
Why use it?
It exposes missing parts and prevents unnecessary components from being added before their responsibilities are clear.

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/interview-building-blocks
Any agent
npx skills add nullhack/temple8 --skill interview-building-blocks
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 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 $0.00026 $0.00431
Opus 5 $0.00013 $0.00216
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash 18c9f9a223f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-building-blocks 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 yesterday.

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/interview-building-blocks/SKILL.md · 14 lines

What it actually says

Interview (Building Blocks)

  1. Load [[requirements/domain-decomposition]], [[requirements/aggregate-boundaries]], [[architecture/quality-attributes]], [[methodology/simplicity-discipline]] — gap analysis, boundary sizing, the quality-attribute taxonomy the coverage check runs over, and the simplicity discipline. This level is structural decomposition, not CIT/Laddering elicitation (those served levels 1–2).
  2. Read the running interview-notes; append the building-block names and boundaries to it.
  3. Capture building-block NAMES and rough boundaries ONLY — no detailed spec (rules, examples, criteria come later in planning). The purpose is to know WHAT building blocks exist, not to specify each.
  4. Ask the simplicity question for each block: "Is this building block load-bearing, or could it collapse into a neighbour?" A block with no unique responsibility a cited need requires is speculative per [[methodology/simplicity-discipline]] — flag it for collapse into a neighbour or drop at consolidation. A block the cited need requires but no current block covers is a gap, flagged here (not silently filled).
  5. Flag rework: IF a finding implies MODIFYING an existing block's behaviour (not adding a new one) THEN mark that block in the decomposition table as rework — modifies existing <block> and record the stakeholder's CIT-grounded reason. This is a requirements-level observation only — discovery does not touch tests. Plan reads these flags at author-test-stubs and marks the matching existing tests @pytest.mark.pending so the build backlog picks them up as rework per [[software-craft/tdd]]. A finding with no such flag is new work.
  6. Run gap analysis: IF a bounded context from cross-cutting maps to no block THEN flag the gap; IF a quality attribute maps to no block THEN flag the gap. Do not silently fill gaps per [[requirements/domain-decomposition]], [[requirements/aggregate-boundaries]].
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. yesterday First seen · 14 lines · 26 tokens per session scan A 18c9f9a223f3

Subscribe to this mod's changes

interview-building-blocks is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 26 tokens to every session and 431 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.