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/test-reference-updategit clone --depth 1 https://github.com/kamiazya/scopesWhat 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 | $0.00750 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade C, and why
test-reference-update scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/test-refs How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Reference Update
Test the task reference update logic used in epic-sync.
Usage
/pm:test-reference-update
Instructions
1. Create Test Files
Create test task files with references:
mkdir -p /tmp/test-refs
cd /tmp/test-refs
# Create task 001
cat > 001.md << 'EOF'
---
name: Task One
status: open
depends_on: []
parallel: true
conflicts_with: [002, 003]
---
# Task One
This is task 001.
EOF
# Create task 002
cat > 002.md << 'EOF'
---
name: Task Two
status: open
depends_on: [001]
parallel: false
conflicts_with: [003]
---
# Task Two
This is task 002, depends on 001.
EOF
# Create task 003
cat > 003.md << 'EOF'
---
name: Task Three
status: open
depends_on: [001, 002]
parallel: false
conflicts_with: []
---
# Task Three
This is task 003, depends on 001 and 002.
EOF
2. Create Mappings
Simulate the issue creation mappings:
# Simulate task -> issue number mapping
cat > /tmp/task-mapping.txt << 'EOF'
001.md:42
002.md:43
003.md:44
EOF
# Create old -> new ID mapping
> /tmp/id-mapping.txt
while IFS=: read -r task_file task_number; do
old_num=$(basename "$task_file" .md)
echo "$old_num:$task_number" >> /tmp/id-mapping.txt
done < /tmp/task-mapping.txt
echo "ID Mapping:"
cat /tmp/id-mapping.txt
3. Update References
Process each file and update references:
while IFS=: read -r task_file task_number; do
echo "Processing: $task_file -> $task_number.md"
# Read the file content
content=$(cat "$task_file")
# Update references
while IFS=: read -r old_num new_num; do
content=$(echo "$content" | sed "s/\b$old_num\b/$new_num/g")
done < /tmp/id-mapping.txt
# Write to new file
new_name="${task_number}.md"
echo "$content" > "$new_name"
echo "Updated content preview:"
grep -E "depends_on:|conflicts_with:" "$new_name"
echo "---"
done < /tmp/task-mapping.txt
4. Verify Results
Check that references were updated correctly:
echo "=== Final Results ==="
for file in 42.md 43.md 44.md; do
echo "File: $file"
grep -E "name:|depends_on:|conflicts_with:" "$file"
echo ""
done
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.
- 2d ago First seen · 135 lines · 0 tokens per session scan C 6cc157c1eb43
test-reference-update 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 750 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review.v1
Review code changes: /review [commit|branch|PR].
diagnose-deeptrace
Run a ZDX deep trace diagnostics session — start, analyze, or clean up deep traces for a user's device.
troubleshoot-user
Cross-product troubleshooting of user connectivity across ZCC, ZDX, ZPA, and ZIA.
audit-ssl
Audit ZIA SSL inspection rules -- list rules by action (INSPECT, DONOTINSPECT, DONOTDECRYPT, BLOCK), identify bypasses, and assess risk.
create-access-rule
Create a ZPA access policy rule with v2 conditions for application access control.
investigate-incident
Investigate security incidents using Z-Insights analytics -- threats, firewall actions, shadow IT, and web traffic.