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/liam-hq/liam/create-internal-issuegit clone --depth 1 https://github.com/liam-hq/liamWhat 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 | $0.00012 | $0.00331 |
| Opus 5 | $0.00006 | $0.00166 |
| Sonnet 5 | $0.00002 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
create-internal-issue 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 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.
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.
What it actually says
Task
Create a new issue in the route06/liam-internal repository using the GitHub CLI.
Follow the general issue creation guidelines in @.claude/commands/create-issue.md with the following specific requirements:
Repository-Specific Requirements
- Repository:
route06/liam-internal - Language: Write both the issue title and body in Japanese
- Command: Use
gh issue create --repo route06/liam-internal
Arguments
$ARGUMENTS
See @.claude/commands/create-issue.md for argument handling guidelines.
Examples
- Simple issue:
/create-internal-issue "バグ: データベース接続タイムアウト" - Complex feature:
/create-internal-issue "現在のログイン方法を改善したい - 詳細な要件があります" - Context-based:
/create-internal-issue "create an issue from what we just discussed" - Empty args:
/create-internal-issue(suggest auto-detection from conversation)
Best Practices
Follow the best practices in @.claude/commands/create-issue.md with special attention to:
- Cross-repository references: When referencing PRs or issues from repositories other than route06/liam-internal (e.g., liam-hq/liam), use the full format
repository#number(e.g.,liam-hq/liam#2991) instead of just#numberto ensure proper GitHub linking
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 · 28 lines · 12 tokens per session scan A 827f12b830d8
create-internal-issue is a command published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 4d ago), licensed Apache-2.0. It adds 12 tokens to every session and 331 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.
Other commands, from other repositories
github-sync
GitHub sync reads FROM living docs. If living docs are stale, GitHub issues will have outdated content.
abandon
Command "abandon" from anton-abyzov/specweave, covering abandon, synopsis, description, options and (required).
overview
Command "overview" from anton-abyzov/specweave, covering commands overview, the core workflow, 1. planning commands, create new increment and 2. implementation commands.
status
Command "status" from anton-abyzov/specweave, covering status, synopsis, description, options and no arguments (default).
ado-pull
Pull latest changes from Azure DevOps (like git pull). Supports increment, project, or full living docs sync.
archive
Manually archive completed increments and sync living docs - NEVER auto-archives, explicit user action only.