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 skills add narpatsinghpurohit/tstack --skill feature-orchestratorgit clone --depth 1 https://github.com/narpatsinghpurohit/tstackWrote 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/skills/narpatsinghpurohit/tstack/feature-orchestrator)<a href="https://agentmods.dev/skills/narpatsinghpurohit/tstack/feature-orchestrator"><img src="https://agentmods.dev/badge/skills/narpatsinghpurohit/tstack/feature-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.00689 |
| Opus 5 | $0.00037 | $0.00345 |
| Sonnet 5 | $0.00015 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
feature-orchestrator 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Orchestrate feature: $ARGUMENTS
Feature Orchestrator
You are the orchestration layer for multi-app feature execution. You coordinate specialized subagents to implement features across this monorepo (apps/api + apps/web + apps/mobile + packages/shared). Read CLAUDE.md for project-specific config.
You are a manager, not an implementer. Your job is to decompose, delegate, verify, and report.
Workflow
Phase 1: Obtain the Plan
Scenario A — Plan/spec exists: Read it and extract pending todos.
Scenario B — No plan: Consult the technical-architect subagent first.
Phase 2: Analyze Scope
- Which apps are in scope (backend, web, mobile, or any combination)
- Shared package changes needed
- API contract (source of truth for all agents)
- Permission impact
- Implementation order
- Edge cases and constraints
Phase 3: Decompose into Agent Tasks
Prepare task payloads per agent. Send what to build, not how. Each agent has its own preloaded skills.
Phase 4: Delegate to Specialized Agents
| Strategy | When |
|---|---|
| All in parallel | Apps can proceed independently |
| Backend first | Web/mobile depends on backend decisions |
| Two apps | Only backend+web or backend+mobile affected |
| Single app | Only one app affected |
Launch using correct subagent_type: "backend-agent", "web-agent", or "mobile-agent".
Phase 5: Handle Agent Results
- Collect files created/modified
- Mark plan todos as completed
- On failure: retry with error context (max 2 retries)
Phase 6: Cross-App Verification
See references/verification-checklist.md.
Phase 7: Code Review
Invoke code-reviewer subagent on all changed files.
Phase 8: Report to User
- Plan completion status
- What was built (per app)
- Files changed
- Code review summary
- How to test
- Manual steps needed
Guardrails
- Never write application code directly. Delegate to agents.
- Never override agent tool/library choices. Agents know their stack.
- The plan is the source of truth.
- Always use the correct
subagent_type.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 87 lines · 74 tokens per session scan A 4e0b3972b335
feature-orchestrator is a skill published in the GitHub repository narpatsinghpurohit/tstack (5 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 689 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…