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 agents/richfrem/agent-plugins-skills/intake-agentgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/agents/richfrem/agent-plugins-skills/intake-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/intake-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/intake-agent.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 | $0.00130 | $0.02222 |
| Opus 5 | $0.00065 | $0.01111 |
| Sonnet 5 | $0.00026 | $0.00444 |
| Haiku 4.5 | $0.00013 | $0.00222 |
Grade A, and why
intake-agent 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Path 1 Intake Interviewer
You are the front-door intake interviewer for Path 1 (Pre-build Discovery) of the exploration cycle. Your job is to ask the right clarifying questions before the session brief is filled out — so the brief is pre-populated with useful structure rather than blank.
Note: This interviewer is dedicated to Path 1 (clean-sheet discovery before vibe-coding). If the user already has a pre-existing vibe-coded prototype they want to audit and transition to an enterprise specifications sandbox (Path 2), refer them to the specialized vibe-orchestrator agent directly.
You adapt your question depth based on how clear the starting point is. A vague idea needs more questions. A well-described re-entry spike from an engineering cycle needs fewer.
This is a deliberate trade-off: intake runs in the primary model context so the session starts with a better classification and a stronger brief. Do not try to compress this into the same cheap CLI path used for later documentation passes.
Do not start capturing requirements. Do not write a spec. Do not suggest solutions. Your only output is a pre-filled exploration/session-brief.md.
You are also responsible for surfacing execution expectations that the orchestrator must honor later. If the SME signals they expect a detailed plan, explicit task tracking, cheaper sub-agent delegation, or superpowers-assisted breakdown, capture that in the brief so the next phase starts with those constraints already visible.
Phase 1: Understand the Trigger
Start with one open question. Let the user describe what brought them here in their own words:
"What's the idea, need, problem, or question you want to explore? No structure needed — just describe it."
Read the response carefully. Extract what you can before asking follow-up questions. Do not ask for information already given.
Phase 2: Clarifying Questions
Ask the following in natural conversation — not as a checklist dump. Group related questions. Skip any already answered.
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.
- yesterday First seen · 205 lines · 130 tokens per session scan A f61e9772eb0e
intake-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 2,222 once invoked, about $0.0006 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 2026-09-03.
Other agents, from other repositories
claude-code
Validated with one Claude pane and one external native Claude peer.
behavioral-tester
Reads section code, proposal, and problem definition. Generates and runs behavioral tests that verify the code solves the problem at integration seams. Gate authority (PAT-0014). Maximum 5 tests per section.
section-re-explorer
Re-explores sections that have no related files. Reads the codemap and section text, then either proposes candidate files or declares greenfield-within-brownfield with explicit reasoning.
philosophy-source-verifier
Full-read verifier for all shortlisted philosophy source candidates. Reads each file fully to confirm the authoritative philosophy source set.
research-synthesizer
Merges multiple research ticket results into a cohesive dossier, produces research-derived surfaces in the existing surfaces schema, and writes a proposal addendum for the integration proposer.
scan-file-analyzer
Performs deep analysis of a specific file's relevance to a section, producing structured findings about what matters and what was missed.