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/locator-addgit 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 | $0.00018 | $0.02079 |
| Opus 5 | $0.00009 | $0.01040 |
| Sonnet 5 | $0.00004 | $0.00416 |
| Haiku 4.5 | $0.00002 | $0.00208 |
Grade A, and why
locator-add 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locator Add
You are tasked with auto-instrumenting React Native library components so that consumers get accessibility locators (testID, accessibilityLabel) for free via prop forwarding plus default derivation from semantic props (text, label, placeholder).
The tool ships in library mode only for v1: it modifies component definitions in libraries like @practo/self-serve. Consumer/app code is not touched. After the library is instrumented and republished, every consumer call site automatically gets a sensible testID without dev effort.
Response format — always:
- What was done (max 2-3 bullets)
- Exactly what the developer needs to do right now
- What happens next
Never narrate reasoning. Direct the next action.
STOP marker: Wherever you see STOP — send your response and wait for developer input before continuing.
Mode picker (front door for empty invocations)
Front door A — picker fires by default
Trigger: $ARGUMENTS is empty.
Use the AskUserQuestion tool.
question: "What do you want to do?"
header: "Mode"
multiSelect: false
options:
- label: "Instrument (apply changes)"
description: "Add testID + accessibilityLabel to a file, directory, or whole library. Example: instrument omega/self-serve/src → every Button/Input/Card gets testID props forwarded, consumer call sites get auto-derived testIDs."
- label: "Dry-run (audit only)"
description: "Print the would-be changes without modifying any file. Recommended for the first run. Example: see that 47 of 60 components in self-serve are candidates, 13 are skipped (compound components)."
- label: "Custom naming (--naming flag)"
description: "Override the default testID naming convention. v1 only supports --naming=role (default). screen/full fall back with a warning. Example: --naming=role on self-serve → Button text='Update Profile' becomes testID='update-profile-button'."
After the answer, prompt for the path: "Path? (file, directory, or library root — must be inside a package.json-rooted library)".
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 · 211 lines · 18 tokens per session scan A 51d595091cdc
locator-add is a command published in the GitHub repository shiyas1331/devkit (4 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,079 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
android
Command "android" from zhagqn/agentwork, covering /android [subcommand] [args] and 执行前必读.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
troubleshoot
Diagnose and resolve iOS issues in code, builds, runtime, and system behavior.
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.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.