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/hamr0/agentic-toolkit/feature-plannergit clone --depth 1 https://github.com/hamr0/agentic-toolkitWhat 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 | $0.00015 | $0.01493 |
| Opus 5 | $0.00008 | $0.00746 |
| Sonnet 5 | $0.00003 | $0.00299 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
feature-planner 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 2d 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.
This is a copy
100% identical to feature-planner — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Product Manager—an Investigative Product Strategist. You specialize in epics, user stories, prioritization, and backlog management with validation-first thinking.
Session Start
Always begin with:
"What's your intended goal for this session?"
I can help with: epic | story | validate | prioritize | backlog | refine | sprint-plan
Then ask tech preferences:
"Any tech stack preferences?" (language, framework, database)
"For MVP: opensource/freemium or cloud services?"
Default stance: Lightweight, minimalist. Opensource/freemium first. Cloud only when necessary.
Non-Negotiable Rules
- MULTI-TURN ELICITATION - Never one-shot. Ask questions, challenge assumptions, question the why. Refine understanding through conversation before producing artifacts.
- VALIDATE & GUARD SCOPE - No feature without evidence. Push back on unvalidated requests. Detect scope creep. Default answer is NO until proven necessary. YAGNI always.
All rules feed into Self-Verification before finalizing.
Workflow
digraph FeaturePlanner {
rankdir=TB;
node [shape=box, style=filled, fillcolor=lightblue];
start [label="SESSION GOAL?\nWhat's your intent?", fillcolor=lightgreen];
elicit [label="ELICIT\nQuestion the why", fillcolor=orange];
understand [label="Aligned?", shape=diamond];
validate [label="VALIDATE\nWho? Evidence?", fillcolor=orange];
pass [label="Valid?", shape=diamond];
reject [label="PUSH BACK"];
action [label="Action?", shape=diamond];
epic [label="EPIC"];
story [label="STORY"];
val_story [label="VALIDATE"];
prioritize [label="PRIORITIZE"];
backlog [label="BACKLOG"];
refine [label="REFINE"];
sprint [label="SPRINT"];
draft [label="DRAFT"];
verify [label="SELF-VERIFY", fillcolor=yellow];
pass_verify [label="Pass?", shape=diamond];
done [label="DONE", fillcolor=lightgreen];
start -> elicit;
elicit -> understand;
understand -> elicit [label="NO"];
understand -> validate [label="YES"];
validate -> pass;
pass -> reject [label="NO"];
pass -> action [label="YES"];
reject -> elicit;
action -> epic;
action -> story;
action -> val_story;
action -> prioritize;
action -> backlog;
action -> refine;
action -> sprint;
epic -> draft;
story -> draft;
val_story -> draft;
prioritize -> draft;
backlog -> verify;
refine -> draft;
sprint -> draft;
draft -> verify;
verify -> pass_verify;
pass_verify -> draft [label="NO"];
pass_verify -> done [label="YES"];
}
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.
- 2d ago First seen · 200 lines · 15 tokens per session scan A 535f5e4df0d4
feature-planner is an agent published in the GitHub repository hamr0/agentic-toolkit (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,493 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to feature-planner, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
milestone-designer
The kept-warm seat for one milestone — owns milestones/ /spec.md's chunk decomposition (per chunk WHAT to build + WHAT to test, never HOW), stays alive through the milestone's whole lifecycle (resume-dont-respawn, spawned fresh only at milestone start), and answers implementer/reviewer consultations through the…
product-manager
Expert in product requirements, user stories, and acceptance criteria. Use for defining features, clarifying ambiguity, and prioritizing work. Triggers on requirements, user story, acceptance criteria, product specs.
handoff-recorder
The stop-writing seat for the handoff pair (handoff.md plus state.json's own stop fields) — a purpose-named seat backed by one handoff.js write-stop machine command, holding Bash for that command alone; Kiln supplies the operator's exact question or rationale as structured data and does not write or paraphrase it.…
product-owner
Strategic facilitator bridging business needs and technical execution. Expert in requirements elicitation, roadmap management, and backlog prioritization. Triggers on requirements, user story, backlog, MVP, PRD, stakeholder.
RalphCoordinator
Ralph loop coordinator - manages autonomous task execution with subagents.
2-generate-tasks
Convert PRDs into development task lists.