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 commands/shiyas1331/devkit/covergit clone --depth 1 https://github.com/shiyas1331/devkitWhat 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 | $0.00022 | $0.02125 |
| Opus 5 | $0.00011 | $0.01063 |
| Sonnet 5 | $0.00004 | $0.00425 |
| Haiku 4.5 | $0.00002 | $0.00213 |
Grade A, and why
cover 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cover with unit tests — router
This is a thin dispatcher. The picker fires when $ARGUMENTS is empty; otherwise the command parses input and delegates to a sub-command. All mode bodies live in commands/cover/<mode>.md — they are self-contained.
Response format — always (except final reports):
- What was done (max 2-3 bullets)
- Exactly what the developer needs to do right now
- What happens next
Never narrate reasoning. Be terse. Directional.
Input
$ARGUMENTS
Routing rules — apply in order
1. Empty input → interactive picker
Trigger: $ARGUMENTS is empty.
Use the AskUserQuestion tool. Do NOT print a menu in text. Do NOT read any help file.
Question 1 — mode selection:
question: "What do you want to do?"
header: "Mode"
multiSelect: false
options:
- label: "Discover untested code"
description: "Scan a package and list untested slices/thunks/hooks/services. Outputs a plan with suggested batches. Example: scan packages/establishment → shows 18 slices, 24 thunks, 12 hooks untested."
- label: "Write tests"
description: "Generate test files for one source file or a batch (slices, thunks, hooks). Runs jest after each. Example: write tests for every slice in packages/establishment in one batch."
- label: "Setup foundation (one-time)"
description: "Scaffold jest.config.js, setup.ts, test-utils, and native module mocks. Run this once on a fresh package before generating tests. Example: setup packages/establishment from zero test infra."
- label: "Show coverage report"
description: "Print coverage delta against baseline plus latent bugs flagged in earlier runs. Example: see that establishment went from 12% to 67% coverage."
After answer, ask for the path (regular text prompt, NOT a tool):
Path? (e.g. `packages/establishment`, or a specific file path for "Write tests"). Type `?` for the verbose reference.
If the user picked "Write tests" AND the path they provide is a directory (not a file), first detect the platform for that path (list <plugin-root>/platforms/, apply each detect.md), then ask the platform-appropriate Question 2 — scope.
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 · 182 lines · 22 tokens per session scan A 8155833719b0
cover is a command published in the GitHub repository shiyas1331/devkit (4 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 2,125 once invoked, about $0.0001 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 commands, from other repositories
feature
Post a feature to the Features Board on production and write tweets.
commit-all
Group all changes semantically and commit each group separately.
validate
Run lint and build to validate changes.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.