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/wshobson/agents/feature-developmentgit clone --depth 1 https://github.com/wshobson/agentsWhat 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 | $0.00012 | $0.03535 |
| Opus 5 | $0.00006 | $0.01767 |
| Sonnet 5 | $0.00002 | $0.00707 |
| Haiku 4.5 | $0.00001 | $0.00353 |
Grade A, and why
feature-development 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Development Orchestrator
CRITICAL BEHAVIORAL RULES
You MUST follow these rules exactly. Violating any of them is a failure.
- Execute steps in order. Do NOT skip ahead, reorder, or merge steps.
- Write output files. Each step MUST produce its output file in
.feature-dev/before the next step begins. Read from prior step files — do NOT rely on context window memory. - Stop at checkpoints. When you reach a
PHASE CHECKPOINT, you MUST stop and wait for explicit user approval before continuing. Use the AskUserQuestion tool with clear options. - Halt on failure. If any step fails (agent error, test failure, missing dependency), STOP immediately. Present the error and ask the user how to proceed. Do NOT silently continue.
- Use only local agents. All
subagent_typereferences use agents bundled with this plugin orgeneral-purpose. No cross-plugin dependencies. - Never enter plan mode autonomously. Do NOT use EnterPlanMode. This command IS the plan — execute it.
Pre-flight Checks
Before starting, perform these checks:
1. Check for existing session
Check if .feature-dev/state.json exists:
-
If it exists and
statusis"in_progress": Read it, display the current step, and ask the user:Found an in-progress feature development session: Feature: [name from state] Current step: [step from state] 1. Resume from where we left off 2. Start fresh (archives existing session) -
If it exists and
statusis"complete": Ask whether to archive and start fresh.
2. Initialize state
Create .feature-dev/ directory and state.json:
{
"feature": "$ARGUMENTS",
"status": "in_progress",
"methodology": "traditional",
"complexity": "medium",
"current_step": 1,
"current_phase": 1,
"completed_steps": [],
"files_created": [],
"started_at": "ISO_TIMESTAMP",
"last_updated": "ISO_TIMESTAMP"
}
Parse $ARGUMENTS for --methodology and --complexity flags. Use defaults if not specified.
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 · 482 lines · 12 tokens per session scan A 0a3315c4c555
feature-development is a command published in the GitHub repository wshobson/agents (39,318 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 3,535 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 2026-08-30.
Other commands, from other repositories
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
doctor
Diagnose installation health. Check Node, CDP bridge, rn-fast-runner (iOS), rn-android-runner (Android), maestro-runner, simulators, Metro, CDP, injected helpers, ffmpeg, physical devices, plugin version, Vercel rules sync. Reports what's missing — does NOT modify your project.
research_web
Conduct extensive web research on technical topics with validated references.