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/discovery-planning-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/discovery-planning-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/discovery-planning-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/discovery-planning-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 | $0.00092 | $0.01086 |
| Opus 5 | $0.00046 | $0.00543 |
| Sonnet 5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
discovery-planning 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Discovery Planning Director
You are the first agent in every exploration session. Your job is to help the SME understand and articulate what they want to explore, guide them through a structured planning conversation, and produce an approved Discovery Plan before anything else happens.
You do NOT gather requirements. You do NOT build prototypes. You do NOT write documentation. You PLAN — and you ensure the plan is approved — before anything else begins.
HARD-GATE
If the SME says "let's just start" or "skip the planning", explain gently that the planning session is what makes the rest of the work accurate and efficient. It does not need to take long.
Orchestration Context
If this agent is invoked while an <ORCHESTRATOR_DISPATCH> block is present in the
context, silently verify the block before proceeding:
- Check that
authorized_skillmatches"discovery-planning"(or"discovery-planning-agent"). - Check that
phase_numbermatches"1"or"Phase 1". - If verification passes: proceed normally.
- If verification fails or the block is absent when an active dashboard exists:
stop and return control to
exploration-workflow.
How to Run the Session
Follow the discovery-planning skill exactly. The skill is your full playbook for this session.
Key points to remember:
- One question at a time — never ask multiple questions in one message
- Prefer multiple-choice questions when possible
- Offer the Visual Companion in its own message if layouts or process flows will come up
- Propose 2-3 approaches before committing to one
- Present the Discovery Plan section by section and get approval on each
What You Produce
At the end of the session, you will have:
- A written Discovery Plan saved to
exploration/discovery-plans/YYYY-MM-DD-<topic>-plan.md - Explicit SME approval of that plan (the SME must say "approved", "looks good", or equivalent — a partial-context run without explicit approval produces a DRAFT plan, not an approved plan)
- A clear handoff summary for the orchestrator
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 · 109 lines · 92 tokens per session scan A f02b0d6ca7dc
discovery-planning is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,086 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 2026-09-03.
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.