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 commands/smart-ai-memory/empathy-framework/plangit clone --depth 1 https://github.com/Smart-AI-Memory/empathy-frameworkWhat 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 | $0.00018 | $0.01765 |
| Opus 5 | $0.00009 | $0.00882 |
| Sonnet 5 | $0.00004 | $0.00353 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
plan 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Planning
Aliases: /approach
Structured approaches for common development tasks with Socratic guidance.
Quick Examples
/plan # Interactive menu
/plan "auth feature" # Start planning a feature
/plan "refactor utils" # Plan a refactoring
Discovery
Question:
header: "Approach"
question: "What development approach do you need?"
options:
- label: "Plan implementation"
description: "Create a plan with Socratic discovery before coding"
- label: "Test-driven development"
description: "Write tests first, then implement (Red-Green-Refactor)"
- label: "Code review"
description: "Review code for quality, security, and best practices"
- label: "Refactor code"
description: "Restructure code without changing behavior"
Plan Implementation
Create a plan with structured Socratic discovery before coding.
Step 1: Understand the Change
Question:
header: "Change Type"
question: "What kind of change are you planning?"
options:
- label: "New feature"
description: "Adding entirely new functionality"
- label: "Enhancement"
description: "Improving or extending existing functionality"
- label: "Bug fix"
description: "Correcting broken behavior"
- label: "Refactor"
description: "Restructuring without changing behavior"
Step 2: Clarify Constraints
Question:
header: "Constraints"
question: "What constraints should I consider?"
multiSelect: true
options:
- label: "Backward compatible"
description: "Must not break existing APIs or behavior"
- label: "Performance critical"
description: "Speed or memory usage is important"
- label: "Security sensitive"
description: "Handles auth, user data, or system access"
- label: "Minimal changes"
description: "Prefer smallest possible footprint"
Step 3: Socratic Exploration
After reading the codebase, I'll ask clarifying questions like:
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 · 285 lines · 18 tokens per session scan A 20384785638a
plan is a command published in the GitHub repository Smart-AI-Memory/empathy-framework (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,765 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
specify
Create or update the feature specification from a natural language feature description.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
speckit.assess.intake
Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note.
specsmd-construction-agent
Command "specsmd-construction-agent" from fabriqaai/specs.md, covering activate construction agent, activation, parameters, critical first steps and your skills.
fire
FIRE orchestrator - Fast Intent-Run Engineering main entry point.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.