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 psenger/ai-agent-skills --skill conventionsgit clone --depth 1 https://github.com/psenger/ai-agent-skillsWrote 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/psenger/ai-agent-skills/conventions)<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/conventions"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/conventions/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/psenger/ai-agent-skills/conventions"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/conventions.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 | $0.00115 | $0.00885 |
| Opus 5 | $0.00057 | $0.00443 |
| Sonnet 5 | $0.00023 | $0.00177 |
| Haiku 4.5 | $0.00012 | $0.00089 |
Grade A, and why
conventions 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- conventions — 100% identical, 0 lines differ
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.
Conventions — ai-agent-skills
Commit Messages
Format: type(scope): subject
- Subject: imperative mood, lowercase, no trailing period, ≤72 characters
- Scope: the skill name (
vault-scribe,handoff) or a repo area (release,ci,readme) - Body: optional — explain why, not what; wrap at 72 chars
- Footer:
Closes #NorFixes #Nfor GitHub issues;BREAKING CHANGE: <desc>for breaking changes
Types
| Type | When |
|---|---|
feat |
New skill or new capability in an existing skill |
fix |
Bug fix in a skill's behaviour or instructions |
chore |
Release commits, tooling, config — no production change |
docs |
README, CHANGELOG, CONTRIBUTING only |
refactor |
Skill restructure with no behaviour change |
test |
Eval additions or changes |
Release commit — always exactly:
chore(release): cut vX.Y.Z release
Examples
feat(handoff): add RESUME workflow and proactive suggestion trigger
fix(vault-scribe): prevent incompatible TOC directives
Closes #1
Branch Names
Pattern: type/issue-number-short-description
feature/14-add-handoff-skill
fix/23-vault-scribe-toc
chore/release-v1-1-0
feature/for new skills or new capabilitiesfix/for bug fixeschore/for release and tooling work- Always include the issue number when one exists
- 2–4 words, hyphenated, no version dots (use dashes)
Pull Requests
Title: same format as a commit — type(scope): subject
Body:
## Summary
- <bullet 1>
- <bullet 2>
## Issue
Closes #N
## Test plan
- [ ] Skill activates on expected triggers
- [ ] Output matches documented format
- [ ] No regressions in adjacent skills
- 2–4 summary bullets
- Always link the issue
- Test plan as checkboxes
CHANGELOG Entries (Keep a Changelog 1.1.0)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 131 lines · 115 tokens per session scan A 3eb423bc8db1
conventions is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 885 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
git-commit-push-pr
Commit, push, and create a PR. Prompts for branch and PR target using quick multi-choice questions. Lightweight alternative to /workflow-ship without preflight checks.
brpr
(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.
plate
Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits…
ag-versionar-codigo
Gerencia git - branches, commits semanticos, PRs, releases e changelog. Use ao final de cada fase ou feature para manter historico limpo.
git-wrapup
Review verified mcp-reporter changes, prepare versioned changelog entries, create logical commits and an annotated local tag. No push or publish.
git
Granular git operations with conventional commits - stage, commit, push, PR, merge. Auto-splits commits by type/scope, blocks on secrets, delegates verbose work to git-manager subagent. GitHub CLI conventions: --body-file for PR bodies, treat gh pr checks exit 8 (pending) as retry not failure, guard run-id assignment…