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/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 | $0.01823 |
| Opus 5 | $0.00000 | $0.00911 |
| Sonnet 5 | $0.00000 | $0.00365 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade B, and why
update 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Check context file ages: `find .claude/context -name "*.md" -type f -exec ls -lt {} + | head -5` How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Context
This command updates the project context documentation in .claude/context/ to reflect the current state of the project. Run this at the end of each development session to keep context accurate.
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.
1. Context Validation
- Run:
ls -la .claude/context/ 2>/dev/null - If directory doesn't exist or is empty:
- Tell user: "❌ No context to update. Please run /context:create first."
- Exit gracefully
- Count existing files:
ls -1 .claude/context/*.md 2>/dev/null | wc -l - Report: "📁 Found {count} context files to check for updates"
2. Change Detection
Gather information about what has changed:
Git Changes:
- Run:
git status --shortto see uncommitted changes - Run:
git log --oneline -10to see recent commits - Run:
git diff --stat HEAD~5..HEAD 2>/dev/nullto see files changed recently
File Modifications:
- Check context file ages:
find .claude/context -name "*.md" -type f -exec ls -lt {} + | head -5 - Note which context files are oldest and may need updates
Dependency Changes:
- Node.js:
git diff HEAD~5..HEAD package.json 2>/dev/null - Python:
git diff HEAD~5..HEAD requirements.txt 2>/dev/null - Check if new dependencies were added or versions changed
3. Get Current DateTime
- Run:
date -u +"%Y-%m-%dT%H:%M:%SZ" - Store for updating
last_updatedfield in modified files
Instructions
1. Systematic Change Analysis
For each context file, determine if updates are needed:
Check each file systematically:
progress.md - Always Update
- Check: Recent commits, current branch, uncommitted changes
- Update: Latest completed work, current blockers, next steps
- Run:
git log --oneline -5to get recent commit messages - Include completion percentages if applicable
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 · 221 lines · 0 tokens per session scan B 8504ff323547
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 1,823 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.