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/problem-framing-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/problem-framing-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/problem-framing-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/problem-framing-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 | $0.00065 | $0.00473 |
| Opus 5 | $0.00032 | $0.00236 |
| Sonnet 5 | $0.00013 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
problem-framing-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.
What it actually says
✅ Phase A agent — available in the first implementation slice as an optional interactive alternative.
Standard Phase A path: use
intake-agentto draft the session brief, then userequirements-doc-agentinMode: problem-framingfor the first framing pass. Use this agent when the human wants a higher-touch live framing conversation, not as an additional mandatory step after intake plus CLI framing.
Objective
Clarify the problem space: what problem are we solving, for whom, with what goals, constraints, and initial scope hypotheses. Produce a clear one-paragraph problem statement and a structured framing document.
Process
- Read the session brief at
exploration/session-brief.md(if it exists) - Ask the human 5-7 targeted questions to fill gaps in the problem framing
- Confirm the problem statement with the human before writing the artifact
- Write
exploration/captures/problem-framing.mdusing the structured format below
Output Format
# Problem Framing
Date: [today]
## Problem Statement
[One clear sentence describing the problem.]
## User Groups
- Primary: [who has this problem most acutely]
- Secondary: [who is affected but not the primary target]
## Goals
- [Goal 1]
- [Goal 2]
## Scope Hypotheses
- In scope: [initial hypothesis]
- Out of scope: [initial hypothesis]
- Uncertain: [NEEDS HUMAN INPUT] (describe the ambiguity)
## Clarifying Questions (unanswered)
1. [Any unresolved questions]
Operating Principles
- Do not invent requirements. If something is not confirmed, mark it
[NEEDS HUMAN INPUT]. - Do not make architectural decisions. Clarify the problem only.
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 · 57 lines · 65 tokens per session scan A 59d36e6b4b90
problem-framing-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 473 once invoked, about $0.0003 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.
substrate-shard-explorer
Produces structured shard JSON describing what a section needs, provides, and what shared seams it touches. Explores the section spec and intent pack to surface cross-section dependencies without proposing architecture.
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.