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 skills add XeldarAlz/everything-claude-unity --skill commit-trailersgit clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xeldaralz/everything-claude-unity/commit-trailers)<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/commit-trailers"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/commit-trailers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/commit-trailers"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/commit-trailers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00037 | $0.00621 |
| Opus 5.5 | $0.00015 | $0.00248 |
| Sonnet 5.5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
commit-trailers 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Commit Trailers
When creating git commit messages, append structured trailers that capture decision context. This metadata makes architectural decisions searchable in git history and helps future developers understand why changes were made the way they were.
Trailers
Required (every commit)
Scope-risk: — How much of the project does this change affect?
low— isolated change, single file or tightly scoped featuremedium— touches multiple systems or changes shared interfaceshigh— modifies shared infrastructure, serialization format, or build pipeline
Conditional (include when applicable)
Constraint: — Architectural constraints that were respected during this change. Reference the rule or convention by name.
Rejected: — Alternatives that were considered and rejected, with brief reason. Helps future developers avoid re-exploring dead ends.
Not-tested: — Known gaps in test coverage or scenarios that weren't verified. Use none if everything is covered.
Format Rules
- Trailers go after a blank line at the end of the commit message body
- One trailer per line
- Keep each trailer under 100 characters
Scope-riskis always present- Omit
Constraintif no specific constraints were relevant - Omit
Rejectedif no alternatives were considered - Omit
Not-testedfor trivial changes; include it for anything non-trivial
Examples
Simple feature addition
Add object pooling for projectiles
Replaces Instantiate/Destroy cycle with a pre-warmed pool of 32.
Pool size is configurable via SerializeField on SpawnSystem.
Scope-risk: low
Constraint: no-alloc-in-update — pool grows only in Awake
Rejected: addressables-pool — overkill for single prefab type
Not-tested: pool exhaustion when max size exceeded during boss fight
Bug fix
Fix enemy health not resetting on respawn
EnemyModel.Health was not reset in ObjectPool.OnGet callback.
Added explicit reset in EnemySystem.OnSpawn().
Scope-risk: low
Not-tested: none
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.
- 1mo ago First seen · 88 lines · 37 tokens per session scan A 900218e54f1a
commit-trailers is a skill published in the GitHub repository XeldarAlz/everything-claude-unity (25 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 621 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
commit-conventions
Enforce conventional commits format with proper types, scopes, and breaking change notation. Use when the user is committing code, writing commit messages, asks about commit format, or when you are about to create a git commit. Always apply this skill before running git commit.
hook-recipes
Ready-to-use hook recipes for common Claude Code automation: prettier on edit, tsc check, console.log warning, git push review, doc blocker. Use when the user wants a specific hook example, asks "how do I auto-format" or "block markdown creation", or needs a hook for a common development workflow.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.