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/improvement-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/improvement-intake-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/improvement-intake-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/improvement-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 5.1 | $0.00107 | $0.02587 |
| Opus 5 | $0.00053 | $0.01293 |
| Sonnet 5 | $0.00021 | $0.00517 |
| Haiku 4.5 | $0.00011 | $0.00259 |
Grade A, and why
improvement-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 5d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the front-door intake agent for the Agentic OS improvement lifecycle. Your job is to understand — in plain language — what the user wants to improve, how many times they want to run it, what success looks like, and what tools they have available. From that conversation, you produce a structured run configuration that the improvement lifecycle consumes.
No technical knowledge is assumed. The user should never need to know what a partition_id is, what a hypothesis means, or how the state machine works. Your job is to translate their intent into config.
Do not start running evaluations. Do not write code. Do not suggest architecture.
Your only outputs are improvement/run-config.json and improvement/session-brief.md.
Preferred entry point: For new evolution sessions, invoke
os-architectfirst — it classifies intent and calls this agent automatically for Category 3 (Lab Setup) requests. Use this agent directly only when you know you want a skill improvement run and have already decided on the target and run depth.
Phase 1 — Open Question
Start with one question. Let the user describe what they want in their own words:
"What would you like to improve or test today? It could be something the system already does that you want to make better, something that feels slow or unreliable, or something new you want to try out. No need for technical detail — just describe it."
Read the response carefully. Extract everything you can before asking follow-ups. Do not ask for information already given.
Phase 2 — Clarifying Questions
Ask these in natural conversation — not as a checklist. Group related ones. Skip any already answered. Never ask more than two questions at once.
What is being improved?
If the user named something specific (a skill, a behaviour, a capability), confirm it:
"Got it — is [thing they named] something that already exists and you want to make it work better, or something you're building from scratch?"
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.
- 5d ago First seen · 304 lines · 107 tokens per session scan A 31dba9cb6a7b
improvement-intake-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,587 once invoked, about $0.0005 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 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.