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 skills add plastic-labs/cursor-honcho --skill honcho-interviewgit clone --depth 1 https://github.com/plastic-labs/cursor-honchoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/plastic-labs/cursor-honcho/honcho-interview)<a href="https://agentmods.dev/skills/plastic-labs/cursor-honcho/honcho-interview"><img src="https://agentmods.dev/badge/skills/plastic-labs/cursor-honcho/honcho-interview.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00765 |
| Opus 5 | $0.00010 | $0.00382 |
| Sonnet 5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
honcho-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honcho Interview
Learn stable, cross-project aspects of the user and store them in Honcho memory.
Guardrails
- Focus on global traits that are unlikely to change between projects.
- Avoid project-specific topics, credentials, addresses, or other sensitive information.
- If an answer is vague, ask one brief clarification before saving a conclusion.
- If the user declines to answer, skip that topic and move on.
- Use existing knowledge to avoid repeating questions the memory already covers.
Step 1: Gather Context
Before asking anything, do two things in parallel:
- Check existing memory: Use the
chattool to ask what is already known about the user. - Scan the environment: Check for files that reveal preferences:
~/.claude/CLAUDE.mdor.claude/CLAUDE.md— explicit user instructionspackage.json— detect package manager (bun/npm/yarn/pnpm).editorconfig,.prettierrc,tsconfig.json— code style- Shell config (
~/.zshrc,~/.bashrc) — OS, shell, env vars .python-version,pyproject.toml— Python tooling
Step 2: Present Findings
Show the user a single summary of everything detected:
Here's what I know so far:
- OS/Shell: macOS, zsh
- Package managers: bun (JS), uv (Python)
- Code style: TypeScript, strict mode
- [any preferences from existing memory]
What I still need to know:
- Communication style (concise vs detailed)
- Code quality priority (clarity, performance, tests)
- Collaboration style (direct changes vs propose first)
Step 3: Fill Gaps (Batch)
Present ALL remaining unknowns as a single numbered list. The user can answer them all at once in one message rather than going back and forth 8 times.
The full set of preferences to cover (skip any already answered by Step 1):
- Communication style: concise answers, detailed explanations, or a mix?
- Tone: direct/professional or conversational?
- Structure: bullet points, step-by-step, or narrative?
- Technical depth: beginner, intermediate, or expert?
- Learning preference: explanations first, examples first, or both?
- Code quality focus: clarity, performance, tests, or minimal changes?
- Collaboration style: make changes directly, propose options, or ask first?
- Environment: OS, shell, package managers, editors?
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.
- 6d ago First seen · 85 lines · 21 tokens per session scan A e915d09341ea
honcho-interview is a skill published in the GitHub repository plastic-labs/cursor-honcho (6 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 765 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.