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/owainlewis/youtube-tutorials/squashgit clone --depth 1 https://github.com/owainlewis/youtube-tutorialsWhat 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 | $0.00266 |
| Opus 5 | $0.00000 | $0.00133 |
| Sonnet 5 | $0.00000 | $0.00053 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
squash 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
Squash
Squash recent commits into a single clean commit.
Input
$ARGUMENTS — number of commits to squash (e.g. "4") or a description of which commits
Instructions
- Run
git log --oneline -10to show recent commits - Identify which commits to squash
- Use
git reset --soft HEAD~Nto uncommit while keeping changes staged - Write a single coherent commit message that summarizes the combined work
- Do NOT just concatenate the old messages — write a new one that captures the intent
Rules
- Never squash commits that have already been pushed to a shared branch
- If commits are already pushed to a feature branch, warn before proceeding
- The new message should describe the overall change, not list individual steps
- Follow the same commit message format (type(scope): subject + body)
Example
Before:
a1b2c3d fix typo in auth handler
d4e5f6g add error handling to login
g7h8i9j add login endpoint
After squash:
feat(auth): add login endpoint with error handling
Adds POST /api/auth/login with credential verification,
JWT token generation, and structured error responses.
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 · 40 lines · 0 tokens per session scan A 969da243232b
squash is a command published in the GitHub repository owainlewis/youtube-tutorials (375 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 266 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 2026-08-30.
Other commands, from other repositories
commit
Commit changes with auto-generated message showing command context, timestamp, and change count.
workflow-concepts
Update the README CONCEPTS section with the latest Claude Code features and concepts.
implement
Execute phased implementation with validation gates.
workflow-claude-commands
Track Claude Code commands report changes and find what needs updating.
workflow-claude-subagents
Track Claude Code subagents report changes and find what needs updating.
weather-orchestrator
Fetch Dubai weather and create an SVG weather card.