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/split-prgit 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 | $0.00018 | $0.00619 |
| Opus 5 | $0.00009 | $0.00309 |
| Sonnet 5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
split-pr 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Split the current large pull request into smaller, manageable PRs following t-wada's TDD practices and skeleton review methodology.
Core Principles
1. Skeleton Review Approach
Reference: https://note.com/knowledgework/n/n50fc54509dd5
First PR should be a skeleton implementation to enable early design feedback.
2. TDD Practice (t-wada style)
Follow t-wada's TDD practice: Each PR must contain both feature and test code together.
3. PR Size Constraints
- Hard limit: 300 lines maximum
- Target range: 100-200 lines (ideal)
- Scope: Both implementation and test code count toward the limit
PR Structure
First PR: Skeleton Implementation
Purpose: Enable skeleton review for early architectural feedback
Contents:
- Core interfaces and contracts
- Basic class/module structure
- Minimal implementation proving the approach
- Basic tests validating structure
- Clear TODOs for subsequent features
Subsequent PRs: Feature Increments
Purpose: Add one small, complete feature
Contents:
- Single feature implementation
- Comprehensive tests for that feature
- Updates to skeleton if needed
- Each PR independently valuable
PR Chaining Strategy
PR1 (Skeleton) → main branch
PR2 (Feature A) → PR1's branch
PR3 (Feature B) → PR2's branch
...continues as needed
Execution Process
Phase 1: Analysis
- Review all current changes
- Identify core abstractions and interfaces
- Map features to logical units
- Estimate line counts per unit
Phase 2: Planning
-
Design skeleton structure
- What interfaces are needed?
- What's the minimal viable structure?
- Which design patterns to showcase?
-
Plan feature PRs
- One feature = one PR
- Each with complete test coverage
- Dependencies between features
- Expected 100-200 lines each
Phase 3: User Approval
Present a detailed split plan showing:
- Skeleton PR contents and purpose
- Each feature PR with:
- Feature description
- Test approach
- Estimated line count
- Dependencies
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 · 101 lines · 18 tokens per session scan A 18eb8017843f
split-pr is a command published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 4d ago), licensed Apache-2.0. It adds 18 tokens to every session and 619 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
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
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.
github-status
Check GitHub sync status for SpecWeave increment. Shows issue number, sync state, progress, last update, and any sync issues. Useful for troubleshooting and monitoring.
cancel-auto
Command "cancel-auto" from anton-abyzov/specweave, covering cancel auto session, usage, options, examples and force cancel without confirmation.
doctor
Run installation health diagnostics - detect ghost commands, stale cache, hash mismatches, and namespace pollution. Use when saying "doctor", "health check", "diagnose installation", or "check installation".