consolidate-interview

A session-closing method that turns interview notes into one approved summary and glossary. It reviews what the stakeholder said and removes unsupported ideas.

In plain words
What is it for?
Use it to consolidate a multi-stage interview, identify important terms, and prepare a small set of grounded requirements for approval.
Why use it?
It prevents speculation from becoming part of the requirements. It also leaves the team with a clear record of the stakeholder’s actual needs.

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

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 407 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 $0.00030 $0.00407
Opus 5 $0.00015 $0.00204
Sonnet 5 $0.00006 $0.00081
Haiku 4.5 $0.00003 $0.00041

Measured 2d ago against content hash 912415609b11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consolidate-interview 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/consolidate-interview/SKILL.md · 14 lines

What it actually says

Consolidate Interview

  1. Load [[requirements/ubiquitous-language]], [[methodology/simplicity-discipline]] — term extraction for the glossary and the simplicity discipline that enforces the drop at consolidation. This level synthesises (Active Listening L3, applied in step 3); it does not probe.
  2. Read the running interview-notes across all three levels.
  3. Apply Active Listening L3: replace the running notes with the full synthesis across all three funnel levels and present it to the stakeholder for approval. The summary reflects what the stakeholder said — no new framing or topic labels.
  4. Drop speculative items per [[methodology/simplicity-discipline]]: every behaviour group, building block, quality attribute, and field surfaced at any funnel level is either grounded in a cited stakeholder need (a CIT incident, a laddered constraint, a named access pattern) or removed from the synthesis before approval. An item with no cited grounding does not reach the contracts — the contracts are the smallest surface that serves the cited needs, neither over- nor under-engineered. Flag each drop in the synthesis so the stakeholder can object; an unchallenged drop is final.
  5. Render docs/glossary.md from .templates/docs/glossary.md.template (substitute <project-name>): one ## Context: <bounded-context> section per context, one ### <Term> entry per term in the template's format (A <category> that <distinguishing characteristic>. + *Aliases: … · Source: …*), from the stakeholder's own terms, so it leads all subsequent naming per [[requirements/ubiquitous-language]].
  6. Exit interview-ready when the stakeholder approves; re-enter the funnel at general whenever plan or build finds the elicitation itself was insufficient.
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 · 14 lines · 30 tokens per session scan A 912415609b11

Subscribe to this mod's changes

consolidate-interview 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 407 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.