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 vibeeval/vibecosystem --skill commit-trailersgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/commit-trailers)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/commit-trailers"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/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/vibeeval/vibecosystem/commit-trailers"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/commit-trailers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01085 |
| Opus 5.5 | $0.00017 | $0.00434 |
| Sonnet 5.5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
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 2mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Trailers -- Structured Decision Context
Supplement conventional commits with structured trailers that preserve the reasoning behind a change. Future maintainers (and future agents) read commit history to understand not just what changed, but why a specific approach was taken.
Standard Trailers
Add these after the commit body, separated by a blank line, when they add value:
Constraint: <external limitation that shaped this approach>
Rejected: <alternative considered and the reason it was rejected>
Confidence: high | medium | low <how certain we are this is correct>
Scope-risk: low | medium | high <blast radius — how much can this break>
Not-tested: <what was not tested and why>
When to Use Each Trailer
| Trailer | When to Include | When to Skip |
|---|---|---|
Constraint |
External limitation forced a non-obvious decision | No external constraints applied |
Rejected |
A reasonable alternative was considered and discarded | Only one approach was viable |
Confidence |
Correctness is uncertain or untested in key areas | Straightforward well-tested change |
Scope-risk |
Change touches shared infrastructure, middleware, auth, or core data paths | Isolated, single-purpose change |
Not-tested |
A gap in test coverage is intentional and known | All paths are tested |
Not every commit needs trailers. A fix: typo in error message needs none.
A new auth middleware affecting every API call needs all five.
Trailer Reference
Constraint
An external limitation — browser API, hosting restriction, library limitation, business rule, or environment constraint — that ruled out the obvious solution.
Constraint: Safari 15 does not support the CSS :has() selector
Constraint: Redis unavailable in staging — in-memory fallback only
Constraint: Must stay on Node 18, no upgrade path in scope
Constraint: Third-party payment API does not support idempotency keys
Rejected
An alternative that was seriously considered. Helps future maintainers understand why the current approach exists instead of the simpler-looking one they are thinking of.
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.
- 2mo ago First seen · 131 lines · 43 tokens per session scan A 11391cd8580e
commit-trailers is a skill published in the GitHub repository vibeeval/vibecosystem (539 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 1,085 once invoked, about $0.0002 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 2026-09-03.
commit-trailers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| commit-trailersvibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| pr-squash-messagescenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 73 | Codex |
| phx-pr-reviewoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 61 | Claude Code, Codex |
| private-secret-scanningjamditis/claude-skills-journalism | Skill | 448 | 2d ago | MIT | A | 40 | Claude Code, Codex |
| branch-and-worktree-workflowcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 70 | Claude Code |
| git-workflowjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 52 | Claude Code |
| shiptobihagemann/turbo | Skill | 419 | 14d ago | MIT | A | 47 | Claude Code, Codex |