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/control-decks/think-it-through/interviewnpx skills add control-decks/think-it-through --skill interviewgit clone --depth 1 https://github.com/control-decks/think-it-throughWhat 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 | $0.00049 | $0.00418 |
| Opus 5 | $0.00024 | $0.00209 |
| Sonnet 5 | $0.00010 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
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.
What it actually says
🔎 Think Interview
ID: think-it-through/interview
HACP: 0.4
Kind: operation
Mode: transform
Traits: read-only, semantic, multi-exchange
Default Binding: Smallest current subject with important missing information
Accepts: hacp/content, hacp/result
Produces: think-it-through/shared-understanding
Duration: until-complete
Effect: Resolve discoverable facts, ask one focused question at a time, and adapt each question to the preceding answer until understanding is sufficient.
Limits: Keep the selected Binding until completion, stop, or redirection. Stay neutral; do not challenge, recommend, or become adversarial testing.
Flow
flowchart TD
A["Selected Binding"] --> B["Reconstruct what is known"]
B --> C["Find smallest important gap"]
C --> D["Search available sources"]
D --> E{"Gap remains?"}
E -->|No| F["Complete shared understanding"]
E -->|Yes| G["Ask one focused question"]
G --> H["Integrate the answer"]
H --> I{"Understanding sufficient?"}
I -->|Yes| F
I -->|No| C
Format
At launch, show the full trace: > 🎯 **<binding>** → 🔎 **INTERVIEW**. On later turns, show > 🔎 **INTERVIEW** · <binding>.
Show Question. Add Why it matters only when the reason is unclear. At completion, state the shared understanding without a recommendation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 46 lines · 49 tokens per session scan A d7ac6b1f7e97
interview is a skill published in the GitHub repository control-decks/think-it-through (3 stars, last pushed 27d ago), licensed MIT. It adds 49 tokens to every session and 418 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 2026-08-31.
Other skills, from other repositories
delegate-setup
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers installed CLIs, proposes a lane map for user approval, and writes global or project config only after explicit yes. Use when the user asks to set up, configure, or…
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…
cursor-delegate
Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…