workflows

A command hub for running automated AI workflows, such as security reviews, bug prediction, testing, and analysis. It routes different tasks to AI models with different levels of capability and cost.

In plain words
What is it for?
It is for running named workflows, listing available workflows, and performing tasks such as security audits, bug prediction, test generation, and code analysis.
Why use it?
It helps choose an appropriate model for each part of a workflow instead of using the same model for every task.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/smart-ai-memory/empathy-framework/workflows
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/empathy-framework

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.02091
Opus 5 $0.00008 $0.01045
Sonnet 5 $0.00003 $0.00418
Haiku 4.5 $0.00002 $0.00209

Measured yesterday against content hash 0d2119234c32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows 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.

.claude/commands/workflows.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated Workflows

Aliases: /wf, /workflow

Run cost-optimized AI workflows that use 3-tier model routing for maximum efficiency.

Quick Examples

/workflows                           # Interactive menu
/workflows run security-audit        # Run security analysis
/workflows run bug-predict ./src     # Predict bugs in src/
/workflows list                      # Show all workflows

How Workflows Save You Money

Workflows use 3-tier model routing to minimize costs while maximizing quality:

Tier Model Cost Used For
CHEAP Claude Haiku $0.80/M Summarization, classification, triage
CAPABLE Claude Sonnet $3.00/M Analysis, code generation, review
PREMIUM Claude Opus $15.00/M Synthesis, architecture, coordination

Typical savings: 60-80% vs using premium models for everything.


Discovery

Question:
  header: "Category"
  question: "What kind of workflow do you need?"
  options:
    - label: "Security & Quality"
      description: "Audit code for vulnerabilities, bugs, and performance issues"
    - label: "Testing"
      description: "Generate tests, boost coverage, run analysis"
    - label: "Documentation"
      description: "Generate and manage documentation"
    - label: "Release"
      description: "Prepare releases, check dependencies"

Security & Quality Workflows

security-audit

Scan code for security vulnerabilities using multi-tier analysis.

/workflows run security-audit
/workflows run security-audit ./src

Stages: scan (CHEAP) → analyze (CAPABLE) → recommend (PREMIUM)

Output: Security findings with severity, recommendations, and remediation steps.


bug-predict

Predict likely bugs using pattern analysis and code smell detection.

/workflows run bug-predict
/workflows run bug-predict ./src

Stages: scan (CHEAP) → analyze (CAPABLE)

Detects:

  • Dangerous eval()/exec() usage
  • Broad exception handling
  • TODO/FIXME comments
  • Code complexity issues

Read the full file on GitHub · 356 lines

Changes

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.

  1. yesterday First seen · 356 lines · 16 tokens per session scan A 0d2119234c32

Subscribe to this mod's changes

workflows 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 16 tokens to every session and 2,091 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.