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/shivaedev/pardes/shell-helpersnpx skills add ShivaeDev/pardes --skill shell-helpersgit clone --depth 1 https://github.com/ShivaeDev/pardesWhat 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 | $0.00050 | $0.01002 |
| Opus 5 | $0.00025 | $0.00501 |
| Sonnet 5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
shell-helpers 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shell-helpers
A small set of portable git/shell helpers for the mechanical parts of orchestration. They install as bin/ executables, so each is a bare command on your PATH — call them directly. Every project-specific is an environment variable with a safe default; nothing is hardcoded.
Reach for these instead of hand-typing the equivalent git incantations: they carry the safety contracts (never reset a dirty tree, never reap a worktree with work in it) that make them safe to lean on unattended.
When to use which
freshen— after a PR merges, or when an agent worktree has drifted, to bring the current checkout to a clean, current baseline and tidy up. Prefer it over a hand-rolledgit fetch && switch && mergewhen you also want setup re-run and merged branches pruned.prune-merged-branches— to clear out local branches whose PRs already merged.reap-stale-worktrees— after a parallel-worktree wave, to clean up worktrees you no longer need.
freshen
freshen brings the current checkout to a clean, current baseline, then tidies up:
- Primary checkout: switches to the default branch and fast-forwards it to origin.
- Linked worktree: fetches with prune, then fast-forwards the worktree's branch to the default branch.
- Then: runs the configured setup command (
SH_SETUP_CMD), prunes merged branches, and — if a managed worktree directory is set — reaps stale worktrees.
Safety contract: freshen NEVER does a destructive reset. If the working tree is dirty, or a worktree cannot fast-forward (it has diverged), it aborts and reports rather than discarding work. So advancing local main after a merge is just:
freshen
If the merge touched the dependency manifest or lockfile, freshen already re-runs SH_SETUP_CMD for you, so regenerated clients and freshly applied migrations stay current — provided that env var points at the repo's setup step.
prune-merged-branches
Deletes local branches whose upstream remote ref is gone (the remote branch was deleted after the PR merged).
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 · 64 lines · 50 tokens per session scan A c6160154b192
shell-helpers is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,002 once invoked, about $0.0003 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
cloudflare-registrar
Cloudflare Registrar: domain availability, prices, registration via mcporter.
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
weekly-report
Structure and data sources for the weekly inventory report. Load this when the task is "weekly report", "Monday report", or "summarize inventory status".
shopify-hydrogen
Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…