agentmods.dev

paul:flows

A command for configuring specialised workflow connections, called flows, between a project and its development skills.

In plain words
What is it for?
It interactively configures skill mappings, adds one mapping, lists the current setup, or checks whether the current phase used its declared workflows.
Why use it?
It makes required skills and their triggers visible, reducing the chance that a project phase skips an expected workflow.

Command

1.2k +6 11d ago A scan 9 tokens original MIT
▶ SEED + PAUL = Claude Code Meta Charlie Automates · about ChristopherKahler/paul · on YouTube →
View the source file ChristopherKahler/paul
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/christopherkahler/paul/flows
Clone the repo
git clone --depth 1 https://github.com/ChristopherKahler/paul
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 $0.00009 $0.00526
Opus 5 $0.00005 $0.00263
Sonnet 5 $0.00002 $0.00105
Haiku 4.5 $0.00001 $0.00053

Measured 2d ago against content hash 33d0492c51a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paul:flows 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.

src/commands/flows.md · 74 lines

What it actually says

When to use:

  • Setting up skill dependencies for a new project
  • Adding a skill mapping to an existing project
  • Checking if required skills were used in current phase
  • Viewing current skill configuration

Subcommands:

  • (no argument): Full interactive configuration
  • add: Quick-add single skill mapping
  • audit: Check current phase against declared flows
  • list: Display current configuration

<execution_context> @/.claude/paul-framework/workflows/configure-special-flows.md @/.claude/paul-framework/references/specialized-workflow-integration.md </execution_context>

@.paul/PROJECT.md @.paul/STATE.md @.paul/SPECIAL-FLOWS.md (if exists)

No argument (full configuration):

  1. Follow @workflows/configure-special-flows.md
  2. Interactive skill discovery and mapping
  3. Generate .paul/SPECIAL-FLOWS.md
  4. Update PROJECT.md with quick reference

add (quick add):

  1. Ask for skill name
  2. Ask for work type trigger
  3. Ask for priority (required/optional)
  4. Append to SPECIAL-FLOWS.md table
  5. Confirm addition

audit (check current phase):

  1. Read .paul/SPECIAL-FLOWS.md
  2. Read .paul/STATE.md for current phase
  3. Check ROADMAP.md for phase skill requirements
  4. Display required skills for this phase
  5. Remind: "Verify invocations before UNIFY"

list (display configuration):

  1. Read .paul/SPECIAL-FLOWS.md
  2. Display formatted summary:
    • Project-level skills (with priority)
    • Phase overrides
    • Templates/assets count

<success_criteria>

  • SPECIAL-FLOWS.md created or updated (for config/add)
  • PROJECT.md quick reference updated (for config)
  • Current phase skills displayed (for audit)
  • Configuration summary shown (for list) </success_criteria>
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. 2d ago First seen · 74 lines · 9 tokens per session scan A 33d0492c51a0

Subscribe to this mod's changes

paul:flows is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 11d ago), licensed MIT. It adds 9 tokens to every session and 526 once invoked, about $0.0000 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.

ai-developmentai-toolsclaudeclaude-codedevelopment-frameworkproject-orchestration
Related

Other commands, from other repositories

safe-refactor

Safe refactoring with automated review, testing, and rollback capabilities.

PaulDuvall/ai-development-patterns · 12 tokens

security-review

Comprehensive security analysis with multi-layer vulnerability detection.

PaulDuvall/ai-development-patterns · 9 tokens

test

Smart test runner with filtering, coverage, and health monitoring.

PaulDuvall/ai-development-patterns · 11 tokens

implement-spec

Implement specification with full traceability and test-driven development.

PaulDuvall/ai-development-patterns · 10 tokens

refactor

Interactive refactoring assistant based on Martin Fowler's refactoring catalog.

PaulDuvall/ai-development-patterns · 12 tokens

deploy_to_docker

Build Docker image and start/redeploy the MCP Task Orchestrator container, reusing the last-used config by default.

jpicklyk/task-orchestrator · 23 tokens