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 agents/jvgomg/podkit/shell-completionsgit clone --depth 1 https://github.com/jvgomg/podkitWhat 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 | $0.00000 | $0.00605 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
shell-completions 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 yesterday.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell Completions
Guidance for working on the shell completion system. See AGENTS.md for project overview.
The podkit completions command generates shell completion scripts (zsh, bash) by walking the Commander.js command tree at runtime. Completions are auto-generated from the actual CLI structure — there is no static completion file to maintain.
How It Works
The completion system supports three levels:
- Subcommands and flags — auto-generated from the Commander.js tree
- Static argument values — options using
.choices()or.addOption(new Option(...).choices([...]))auto-complete their values (e.g.--quality→max,high,medium,low) - Dynamic argument values —
--deviceand--collectioncomplete with names from the user's config via a hidden__completecommand
Impact on CLI Changes
- Adding or removing commands, subcommands, or options requires no changes to the completions system. The generator reads the Commander.js program tree dynamically, so new commands automatically appear in completions.
- When adding an option with known values, use
.addOption(new Option(...).choices([...]))instead of.option()— the completion generator picks upargChoicesautomatically. - For options with a custom parse function (like sync's repeatable
-t, --type), usenew Option()with manualargChoicesassignment to preserve the parser while exposing choices for completions. - The hidden
__completecommand reads the config file directly (no validation) and outputs names. Dynamic completions for new option types require updatingextractCommandTree(to tag the option) and the zsh/bash generators. - The
--cmdflag oncompletions zsh/bashcontrols which binary the dynamic helpers call. This is important for dev binaries with non-standard names (e.g.podkit-dev).
Testing Completions During Development
The completions generator derives the function prefix from --cmd: podkit-dev → _podkit_dev,
podkit → _podkit. This means each binary gets its own isolated function namespace and the
two completion scripts can coexist without clobbering each other.
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.
- yesterday First seen · 38 lines · 0 tokens per session scan A d32c025205e1
shell-completions is an agent published in the GitHub repository jvgomg/podkit (39 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 605 tokens. 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 2026-09-01.
Other agents, from other repositories
AGENTS
Use uv for every Python command in this repo. Do not use bare python, pip, poetry, or conda.
CONTEXT
Agent "CONTEXT" from TheRealSavi/iOpenPod, covering iopenpod and language.
accessibility-reviewer
Reviews Android Compose / iOS SwiftUI changes for screen-reader and reduce-motion regressions. Use proactively after any UI change, before opening a PR that touches ui/ or iosApp/ Views, or when asked to check TalkBack/VoiceOver accessibility. A core user base is blind and visually impaired — accessibility is treated…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.