load

An interactive project-spec loader that finds relevant rules, decisions, patterns, and bug notes by keyword, type, or tag.

In plain words
What is it for?
Use it to browse all specs or find entries such as API-routing notes, security rules, bugs, or architecture decisions.
Why use it?
It helps you retrieve project knowledge without opening and searching every specification file manually.

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/catlog22/claude-code-workflow/load
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,911 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 $0.00018 $0.02911
Opus 5 $0.00009 $0.01456
Sonnet 5 $0.00004 $0.00582
Haiku 4.5 $0.00002 $0.00291

Measured 2d ago against content hash d58575e28938, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

load 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.

.claude/commands/workflow/spec/load.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Load Command (/workflow:spec:load)

Overview

Interactive entry point for loading and browsing project specs. Asks the user what they need, then routes to the appropriate spec content based on keywords, type filters, or tag filters.

Design: Menu-driven → keyword match → load & display. No file modifications.

Note: This command may be called by other workflow commands. Upon completion, return immediately to continue the calling workflow.

Usage

/workflow:spec:load                    # Interactive menu
/workflow:spec:load "api routing"      # Direct keyword search
/workflow:spec:load --type bug         # Filter by knowledge type
/workflow:spec:load --tag security     # Filter by domain tag
/workflow:spec:load --all              # Load all specs

Execution Process

Input Parsing:
   ├─ Parse --all flag → loadAll = true | false
   ├─ Parse --type (bug|pattern|decision|rule)
   ├─ Parse --tag (domain tag)
   └─ Parse keyword query (positional text)

Decision:
   ├─ --all → Load all specs (Path C)
   ├─ --type or --tag or keyword → Direct filter (Path B)
   └─ No args → Interactive menu (Path A)

Path A: Interactive Menu
   ├─ Step A1: Ask user intent
   ├─ Step A2: Route to action
   └─ Step A3: Display results

Path B: Direct Filter
   ├─ Step B1: Build filter from args
   ├─ Step B2: Search specs
   └─ Step B3: Display results

Path C: Load All
   └─ Display all spec contents

Output:
   └─ Formatted spec entries matching user query

Implementation

Step 1: Parse Input

const args = $ARGUMENTS
const argsLower = args.toLowerCase()

const loadAll = argsLower.includes('--all')
const hasType = argsLower.includes('--type')
const hasTag = argsLower.includes('--tag')

let type = hasType ? args.match(/--type\s+(\w+)/i)?.[1]?.toLowerCase() : null
let tag = hasTag ? args.match(/--tag\s+([\w-]+)/i)?.[1]?.toLowerCase() : null

// Extract keyword query (everything that's not a flag)
let keyword = args
  .replace(/--type\s+\w+/gi, '')
  .replace(/--tag\s+[\w-]+/gi, '')
  .replace(/--all/gi, '')
  .replace(/^["']|["']$/g, '')
  .trim()

// Validate type
if (type && !['bug', 'pattern', 'decision', 'rule'].includes(type)) {
  console.log("Invalid type. Use 'bug', 'pattern', 'decision', or 'rule'.")
  return
}

Read the full file on GitHub · 393 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. 2d ago First seen · 393 lines · 18 tokens per session scan A d58575e28938

Subscribe to this mod's changes

load is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 2,911 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.