Borrowing it
Nothing to install: this file belongs to kamiazya/scopes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamiazya/scopes/main/.claude/commands/pm/epic-sync.mdgit 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-sync)<a href="https://agentmods.dev/commands/kamiazya/scopes/epic-sync"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/epic-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kamiazya/scopes/epic-sync"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/epic-sync.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03668 |
| Opus 5.5 | $0.00000 | $0.01467 |
| Sonnet 5.5 | $0.00000 | $0.00734 |
| Haiku 4.5 | $0.00000 | $0.00367 |
Grade B, and why
epic-sync scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
parallel_count=$(grep -l '^parallel: true' .claude/epics/$ARGUMENTS/[0-9]*.md 2>/dev/null | wc -l) How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic Sync
Push epic and tasks to GitHub as issues.
Usage
/pm:epic-sync <feature_name>
Quick Check
# Verify epic exists
test -f .claude/epics/$ARGUMENTS/epic.md || echo "❌ Epic not found. Run: /pm:prd-parse $ARGUMENTS"
# Count task files
ls .claude/epics/$ARGUMENTS/*.md 2>/dev/null | grep -v epic.md | wc -l
If no tasks found: "❌ No tasks to sync. Run: /pm:epic-decompose $ARGUMENTS"
Instructions
1. Create Epic Issue
Strip frontmatter and prepare GitHub issue body:
# Extract content without frontmatter
sed '1,/^---$/d; 1,/^---$/d' .claude/epics/$ARGUMENTS/epic.md > /tmp/epic-body-raw.md
# Remove "## Tasks Created" section and replace with Stats
awk '
/^## Tasks Created/ {
in_tasks=1
next
}
/^## / && in_tasks {
in_tasks=0
# When we hit the next section after Tasks Created, add Stats
if (total_tasks) {
print "## Stats\n"
print "Total tasks: " total_tasks
print "Parallel tasks: " parallel_tasks " (can be worked on simultaneously)"
print "Sequential tasks: " sequential_tasks " (have dependencies)"
if (total_effort) print "Estimated total effort: " total_effort " hours"
print ""
}
}
/^Total tasks:/ && in_tasks { total_tasks = $3; next }
/^Parallel tasks:/ && in_tasks { parallel_tasks = $3; next }
/^Sequential tasks:/ && in_tasks { sequential_tasks = $3; next }
/^Estimated total effort:/ && in_tasks {
gsub(/^Estimated total effort: /, "")
total_effort = $0
next
}
!in_tasks { print }
END {
# If we were still in tasks section at EOF, add stats
if (in_tasks && total_tasks) {
print "## Stats\n"
print "Total tasks: " total_tasks
print "Parallel tasks: " parallel_tasks " (can be worked on simultaneously)"
print "Sequential tasks: " sequential_tasks " (have dependencies)"
if (total_effort) print "Estimated total effort: " total_effort
}
}
' /tmp/epic-body-raw.md > /tmp/epic-body.md
# Determine epic type (feature vs bug) from content
if grep -qi "bug\|fix\|issue\|problem\|error" /tmp/epic-body.md; then
epic_type="bug"
else
epic_type="feature"
fi
# Create epic issue with labels
epic_number=$(gh issue create \
--title "Epic: $ARGUMENTS" \
--body-file /tmp/epic-body.md \
--label "epic,epic:$ARGUMENTS,$epic_type" \
--json number -q .number)
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.
- 2mo ago First seen · 428 lines · 0 tokens per session scan B f8b8117e9ac6
epic-sync is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 11mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,668 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.
epic-sync compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| epic-synckamiazya/scopes | Command | 2 | 11mo ago | Apache-2.0 | B | 0 | Claude Code |
| diagnose-deeptracezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 29 | Claude Code |
| troubleshoot-experiencezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 25 | Claude Code |
| app-healthzscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 16 | Claude Code |
| compare-locationszscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 20 | Claude Code |
| investigate-alertszscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 23 | Claude Code |
| investigate-sandboxzscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 30 | Claude Code |