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.
git clone --depth 1 https://github.com/chohra-med/expo_boilerplateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/chohra-med/expo_boilerplate/generate-agents)<a href="https://agentmods.dev/commands/chohra-med/expo_boilerplate/generate-agents"><img src="https://agentmods.dev/badge/commands/chohra-med/expo_boilerplate/generate-agents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chohra-med/expo_boilerplate/generate-agents"><img src="https://agentmods.dev/badge/commands/chohra-med/expo_boilerplate/generate-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00896 |
| Opus 5 | $0.00000 | $0.00448 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
generate-agents 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 10d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: generate-agents — bind the 6 SDD agents to this project's rules
The keystone of the generative pipeline. The agents ship generic; this makes them bound to THIS project's rules. After it runs, the
sdd-implementerliterally contains this project's coding rules, thesdd-testercontains its real test command, thesdd-reviewercontains its review bar — not a pointer, the actual rules. Feedback that updates the rules re-runs this so the agents track them.
Invocation
spec-harness generate-agents [<target>] # stage the work order (bin/sh-gen-agents.sh)
Or the spec-harness-generate-agents skill in Claude Code (it executes the work order end-to-end).
install/init call this as the final step, so a freshly-installed repo already has bound agents
(or, if it has no rules yet, a clear instruction to generate rules first).
How it works
bin/sh-gen-agents.shchecks the repo has rules.- No rules → it prints the rules-DISCOVERY prompt (3 sources — see
rules.md) and stops. Generate rules first (spec-harness rules --generate), then come back. - Rules exist → it writes a work order to
.claude/agents/.generate-agents.prompt.md.
- No rules → it prints the rules-DISCOVERY prompt (3 sources — see
- You (the agent/skill) execute the work order: for each of the 6 agent files, replace the text
between
<!-- GEN:rules START -->and<!-- GEN:rules END -->with that agent's concern rules, synthesized from this project's real rules. Keep the markers.
The concern each agent gets (one per agent)
| Agent | Inject | Synthesized from |
|---|---|---|
sdd-implementer |
Coding + Packages | RULES.md (Coding,Packages) · frequent_rules.md · real source files |
sdd-researcher |
Architecture + Packages | RULES.md (Architecture,Packages) · 30-tech.md · context_map.md |
sdd-planner |
Architecture | RULES.md (Architecture) · context_map.md · 20-system.md |
sdd-tester |
Testing | RULES.md (Testing) · 30-tech.md ## Commands · the test config |
sdd-reviewer |
Reviewing + Coding | RULES.md (Reviewing,Coding) · frequent_rules.md |
sdd-verifier |
Goal end-state + verify command | goal.md · RULES.md (Testing) · 30-tech.md ## Commands |
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.
- 10d ago First seen · 51 lines · 0 tokens per session scan A 62732ea8ed1c
generate-agents is a command published in the GitHub repository chohra-med/expo_boilerplate (33 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 896 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 2026-08-30.
Other commands, from other repositories
arc-skill
You are scaffolding a new React Native (Expo) project using the arc-skill architecture.
arc-connect
Connect API layer, storage, state management, authentication, and i18n to an existing React Native Expo project. Use after arc-scaffold to add backend integration. Trigger when the user mentions adding API calls, auth flow, login, storage, state management, internationalization, backend connection, or data fetching to…
arc-ui
Add theme system, reusable components, screen layouts, and mobile UX design to a React Native Expo project. Use after arc-scaffold to build the visual layer. Trigger when the user wants to add a theme, dark mode, UI components, buttons, inputs, screen layouts, design system, or visual polish to their React Native app.
arc-audit
Audit a React Native Expo project for mobile UX issues, performance problems, and architecture violations. Use to check code quality against arc-skill best practices. Trigger when the user asks to review code, check for issues, wants a health check, mentions touch targets, accessibility, performance audit, or says 'is…
arc-feature
Add a complete new feature domain to an existing React Native Expo project — types, API module, React Query hooks, screen, and components in one go. Use when adding a new entity like products, orders, chat, users, recipes, or any CRUD resource. Trigger when the user says 'add a feature', 'create a new screen for X'…
arc-scaffold
Scaffold a new React Native Expo project with folder structure, dependencies, TypeScript config, linting, and navigation shell. Use when starting a new mobile app from scratch, when the user says 'create a new app', 'start a project', 'set up React Native', 'init Expo app', or needs project boilerplate. Trigger this…