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 Eliyce/paqad-ai --skill git-workflowgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/git-workflow)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/git-workflow"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/git-workflow/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/eliyce/paqad-ai/git-workflow"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/git-workflow.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 | $0.00144 | $0.01784 |
| Opus 5.5 | $0.00058 | $0.00714 |
| Sonnet 5.5 | $0.00029 | $0.00357 |
| Haiku 4.5 | $0.00014 | $0.00178 |
Grade A, and why
git-workflow 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules
- Change .paqad/configs/git-workflow/ only through this skill's scripts. Never edit those files with Edit, Write or a shell command: paqad blocks direct edits, and a change that skips the scripts is never checked or recorded.
- Base every proposal on what the scripts found. When history is mixed, ask the team; don't pick for them. When something can't be read, say it's unknown, never that it doesn't exist.
- Record every answer as a decision, so the team can see later why each rule exists.
What It Does
One skill is in charge of .paqad/configs/git-workflow/, the five files that hold this
team's rules for tickets, branches, commits, pull requests and how strictly they're
checked (tickets.yaml, branches.yaml, commits.yaml, pull-requests.yaml,
enforcement.yaml). It handles three cases:
- first setup from the repo's history, during
create documentation - a new project with no history
- any later change the team asks for
The scripts read git and gh, propose with evidence, validate and write. Your job is
only to ask the team and explain.
Use This When
create documentationreaches its git workflow step (first setup).- The repo has no remote, fewer than 20 main-line commits, or no branches besides the
base (the scripts report
mode: new-project). - Someone asks to change how branches are named, where changes start, how commits or PR titles are written, which labels or reviewers a PR gets, which tickets a change links, how ticket statuses move, or how strictly any of that is checked. This applies whatever workflow the request routed to, and even when the request doesn't mention the config.
Inputs
project_root(path, optional): defaults to cwd.flow(string, optional):first-setup,new-projectorchange. Picked from the request when not given.
Procedure
Every script prints JSON on stdout, never prompts, and exits 0 on success, 1 on invalid
input or config, and 2 when git or gh failed.
What ships with it
13 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.
- agents/openai.yaml 249 B
- assets/answers.template.json 69 B
- assets/change.template.json 114 B
- assets/final-message.txt 197 B
- references/questions.md 2.5 KB
- references/settings.md 11 KB
- references/signals.md 3.5 KB
- references/summaries.md 1.2 KB
- scripts/apply.mjs 2.1 KB runs code
- scripts/change.mjs 1.9 KB runs code
- scripts/check.mjs 1.8 KB runs code
- scripts/propose.mjs 1.6 KB runs code
- skill.meta.yaml 380 B
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 · 115 lines · 144 tokens per session scan A 366db4ff198b
git-workflow is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 1,784 once invoked, about $0.0006 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 2026-11-04.
git-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-workflowEliyce/paqad-ai | Skill | 8 | today | MIT | A | 144 | Claude Code, Codex |
| lore-commitInsajin/autopus-adk | Skill | 111 | 1mo ago | MIT | A | 20 | Claude Code, Codex |
| autofix-prQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 141 | Claude Code |
| cw-landHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 44 | Claude Code, Codex |
| git-commitUfoMiao/zcf | Skill | 6.1k | 8d ago | MIT | A | 41 | Claude Code |
| git-mastercode-yeongyu/lazycodex | Skill | 3.9k | yesterday | MIT | A | 93 | Codex |
| ghbubbuild/bub | Skill | 1.7k | yesterday | Apache-2.0 | A | 96 | Claude Code, Codex |