Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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-oneshot)<a href="https://agentmods.dev/commands/kamiazya/scopes/epic-oneshot"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/epic-oneshot.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 5.1 | $0.00000 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade B, and why
epic-oneshot scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
if grep -q "github:" .claude/epics/$ARGUMENTS/epic.md; then What it actually says
Epic Oneshot
Decompose epic into tasks and sync to GitHub in one operation.
Usage
/pm:epic-oneshot <feature_name>
Instructions
1. Validate Prerequisites
Check that epic exists and hasn't been processed:
# Epic must exist
test -f .claude/epics/$ARGUMENTS/epic.md || echo "❌ Epic not found. Run: /pm:prd-parse $ARGUMENTS"
# Check for existing tasks
if ls .claude/epics/$ARGUMENTS/[0-9]*.md 2>/dev/null | grep -q .; then
echo "⚠️ Tasks already exist. This will create duplicates."
echo "Delete existing tasks or use /pm:epic-sync instead."
exit 1
fi
# Check if already synced
if grep -q "github:" .claude/epics/$ARGUMENTS/epic.md; then
echo "⚠️ Epic already synced to GitHub."
echo "Use /pm:epic-sync to update."
exit 1
fi
2. Execute Decompose
Simply run the decompose command:
Running: /pm:epic-decompose $ARGUMENTS
This will:
- Read the epic
- Create task files (using parallel agents if appropriate)
- Update epic with task summary
3. Execute Sync
Immediately follow with sync:
Running: /pm:epic-sync $ARGUMENTS
This will:
- Create epic issue on GitHub
- Create sub-issues (using parallel agents if appropriate)
- Rename task files to issue IDs
- Create worktree
4. Output
🚀 Epic Oneshot Complete: $ARGUMENTS
Step 1: Decomposition ✓
- Tasks created: {count}
Step 2: GitHub Sync ✓
- Epic: #{number}
- Sub-issues created: {count}
- Worktree: ../epic-$ARGUMENTS
Ready for development!
Start work: /pm:epic-start $ARGUMENTS
Or single task: /pm:issue-start {task_number}
Important Notes
This is simply a convenience wrapper that runs:
/pm:epic-decompose/pm:epic-sync
Both commands handle their own error checking, parallel execution, and validation. This command just orchestrates them in sequence.
Use this when you're confident the epic is ready and want to go from epic to GitHub issues in one step.
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.
- 5d ago First seen · 90 lines · 0 tokens per session scan B d7a6267f3c63
epic-oneshot 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 572 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.