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/creategit 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 | $0.01642 |
| Opus 5 | $0.00000 | $0.00821 |
| Sonnet 5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
create 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 yesterday.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Initial Context
This command creates the initial project context documentation in .claude/context/ by analyzing the current project state and establishing comprehensive baseline documentation.
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 Directory Check
- Run:
ls -la .claude/context/ 2>/dev/null - If directory exists and has files:
- Count existing files:
ls -1 .claude/context/*.md 2>/dev/null | wc -l - Ask user: "⚠️ Found {count} existing context files. Overwrite all context? (yes/no)"
- Only proceed with explicit 'yes' confirmation
- If user says no, suggest: "Use /context:update to refresh existing context"
- Count existing files:
2. Project Type Detection
- Check for project indicators:
- Node.js:
test -f package.json && echo "Node.js project detected" - Python:
test -f requirements.txt || test -f pyproject.toml && echo "Python project detected" - Rust:
test -f Cargo.toml && echo "Rust project detected" - Go:
test -f go.mod && echo "Go project detected"
- Node.js:
- Run:
git status 2>/dev/nullto confirm this is a git repository - If not a git repo, ask: "⚠️ Not a git repository. Continue anyway? (yes/no)"
3. Directory Creation
- If
.claude/doesn't exist, create it:mkdir -p .claude/context/ - Verify write permissions:
touch .claude/context/.test && rm .claude/context/.test - If permission denied, tell user: "❌ Cannot create context directory. Check permissions."
4. Get Current DateTime
- Run:
date -u +"%Y-%m-%dT%H:%M:%SZ" - Store this value for use in all context file frontmatter
Instructions
1. Pre-Analysis Validation
- Confirm project root directory is correct (presence of .git, package.json, etc.)
- Check for existing documentation that can inform context (README.md, docs/)
- If README.md doesn't exist, ask user for project description
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.
- yesterday First seen · 162 lines · 0 tokens per session scan A b9001ce0c6f1
create 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 1,642 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
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.