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/kamiazya/scopes/epic-decomposegit clone --depth 1 https://github.com/kamiazya/scopesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/kamiazya/scopes/epic-decompose)<a href="https://agentmods.dev/commands/kamiazya/scopes/epic-decompose"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/epic-decompose.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01905 |
| Opus 5 | $0.00000 | $0.00953 |
| Sonnet 5 | $0.00000 | $0.00381 |
| Haiku 4.5 | $0.00000 | $0.00191 |
Grade A, and why
epic-decompose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic Decompose
Break epic into concrete, actionable tasks.
Usage
/pm:epic-decompose <feature_name>
Required Rules
IMPORTANT: Before executing this command, read and follow:
.claude/rules/datetime.md- For getting real current date/time
Preflight Checklist
Before proceeding, complete these validation steps. Do not bother the user with preflight checks progress ("I'm not going to ..."). Just do them and move on.
-
Verify epic exists:
- Check if
.claude/epics/$ARGUMENTS/epic.mdexists - If not found, tell user: "❌ Epic not found: $ARGUMENTS. First create it with: /pm:prd-parse $ARGUMENTS"
- Stop execution if epic doesn't exist
- Check if
-
Check for existing tasks:
- Check if any numbered task files (001.md, 002.md, etc.) already exist in
.claude/epics/$ARGUMENTS/ - If tasks exist, list them and ask: "⚠️ Found {count} existing tasks. Delete and recreate all tasks? (yes/no)"
- Only proceed with explicit 'yes' confirmation
- If user says no, suggest: "View existing tasks with: /pm:epic-show $ARGUMENTS"
- Check if any numbered task files (001.md, 002.md, etc.) already exist in
-
Validate epic frontmatter:
- Verify epic has valid frontmatter with: name, status, created, prd
- If invalid, tell user: "❌ Invalid epic frontmatter. Please check: .claude/epics/$ARGUMENTS/epic.md"
-
Check epic status:
- If epic status is already "completed", warn user: "⚠️ Epic is marked as completed. Are you sure you want to decompose it again?"
Instructions
You are decomposing an epic into specific, actionable tasks for: $ARGUMENTS
1. Read the Epic
- Load the epic from
.claude/epics/$ARGUMENTS/epic.md - Understand the technical approach and requirements
- Review the task breakdown preview
2. Analyze for Parallel Creation
Determine if tasks can be created in parallel:
- If tasks are mostly independent: Create in parallel using Task agents
- If tasks have complex dependencies: Create sequentially
- For best results: Group independent tasks for parallel creation
3. Parallel Task Creation (When Possible)
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.
- 4d ago First seen · 231 lines · 0 tokens per session scan A d6c926aa7388
epic-decompose is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,905 tokens. 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 2026-08-31.
Other commands, from other repositories
diagnose-deeptrace
Run a ZDX deep trace diagnostics session — start, analyze, or clean up deep traces for a user's device.
troubleshoot-experience
Troubleshoot a user's digital experience using ZDX scores, metrics, and network path data.
app-health
Analyze application health across the organization using ZDX scores and metrics.
audit-software
Audit software inventory across devices using ZDX data for compliance and vulnerability assessment.
compare-locations
Compare digital experience across locations, departments, or geolocations using ZDX.
investigate-alerts
Investigate active and historical ZDX alerts to understand scope, root cause, and impact.