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 skills/zfinix/aster/git-workflownpx skills add Zfinix/aster --skill git-workflowgit clone --depth 1 https://github.com/Zfinix/asterWhat 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 | $0.00048 | $0.00470 |
| Opus 5 | $0.00024 | $0.00235 |
| Sonnet 5 | $0.00010 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
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.
What it actually says
Git workflow
- Never use interactive flags. There is no terminal to answer them, so the
command hangs until it is killed. Never:
git rebase -i,git add -i,git add -p,git commitwithout-m. - Disarm the pager.
git --no-pager log,git --no-pager diff, or bound with| head -40. A paged command hangs exactly like an interactive one. - Commit only when the user asked for a commit. Finishing an edit is not permission to commit it.
- Stage named files.
git add src/lib.rs src/tests/lib_test.rs. Nevergit add -Aorgit add .: they sweep in unrelated changes and scratch files. - Conventional commit message, one line.
type(scope): summary, imperative and lowercase, no trailing period. Write:fix(sandbox): keep partial output on timeout. Never a multi-paragraph body unless the user asked for one. - No attribution trailers. Never add
Co-Authored-Byor tool-generated footers unless the user asks. - Branch before touching the default branch. Asked to push while on main/master: create a branch and push that, or ask. Never push to the default branch as a side effect.
- Batch state checks into one call.
bash -lc "git status --short; git log --oneline -5; git diff --stat". - Destructive commands need an explicit ask.
reset --hard,checkout -- .,clean -f,push --force: only when the user asked for that outcome, and state first what will be lost. Preferpush --force-with-leaseover--force.
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 · 33 lines · 48 tokens per session scan A eeff6b5f1f19
git-workflow is a skill published in the GitHub repository Zfinix/aster (40 stars, last pushed 7d ago), licensed Apache-2.0. It adds 48 tokens to every session and 470 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
Apify
Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business…
using-git-worktrees
Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.
weavebench-cua-reproduce
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up dependencies, download WeaveBench assets, prepare the 120G VM, configure Qwen/Anthropic-compatible APIs, run smoke tests, launch full or subset evaluations, inspect logs, or summarize scores for…
memstack-content-product-description
Use this skill when the user says 'product description', 'product listing', 'product copy', 'Amazon listing', 'Shopify listing', 'e-commerce copy', or needs conversion-optimized product descriptions with benefit-driven headlines and platform-specific SEO. Do NOT use for pricing strategy or sales funnels.
om-gap-analysis
Grounded platform gap analysis at engagement scale — turn a folder of client docs into an Epic/Story tree where every coverage verdict is re-run by executable gates against a validated checkout of the platform, scored in atomic commits, license-tier-tagged, and synthesized into a client-facing summary + backlog. Use…
new-plugin
Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…