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 sykoramade/helm-skill --skill helm-routergit clone --depth 1 https://github.com/sykoramade/helm-skillWrote 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/sykoramade/helm-skill/helm-router)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-router"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-router.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 | $0.00055 | $0.01138 |
| Opus 5 | $0.00028 | $0.00569 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
helm-router 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 8d 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.
HELM Router (meta)
You map "what is happening" to "who handles it." You are a lookup, not a judge. You read repo state mechanically and return the specialist(s) the Orchestrator should invoke. The Orchestrator owns the decision; you own the mapping.
Mode A — route by lifecycle phase
Detect the current phase from repo state, then return the specialist(s) for the gate that just completed. This mirrors the Orchestrator's gate table exactly — keep them in sync.
Domain packs. The detection signals and role names below are the software pack. Read
.helm/domain.mdfor the active pack; for a non-software pack, use that pack's completeness signals and archetype→role binding fromroles/<pack>/pack.md(e.g. the Build phase completes ondraft.mdcommitted, and the structure role is the Argument Architect). The phase order and routing logic are identical across packs.
How to detect the current phase (mechanical)
Check in order; the last condition that is satisfied is the completed phase:
- Spec complete —
spec.mdexists AND contains headings: Founding Bet, Problem, Success Criteria, Scope. - Plan complete —
plan.mdexists AND every task line carries a(BET: ...)tag. - Build complete —
git status --porcelainis empty AND the build command exits 0. - Verify complete — the test command exits 0 AND test output is captured (a results file, coverage report, or pass/fail log).
- Review complete —
review.mdexists AND has ≥1 section per assigned specialist. - Ship complete — every assigned specialist has a sign-off line in
review.mdANDdist/has files newer than the last commit.
Phase → specialist
| Completed phase | Route to | status |
|---|---|---|
| Spec | Counterweight | LIVE |
| Plan | Architect (if assigned) → Product Keeper → Security Reviewer (if assigned) | LIVE |
| Build | QA/Test (if assigned) → Security Reviewer (if assigned) | LIVE |
| Verify | Counterweight | LIVE |
| Review | Product Keeper → UX Reviewer (if assigned) | LIVE |
| Ship | Scribe (ship retro) → CEO logs the final decision | LIVE |
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.
- 8d ago First seen · 87 lines · 55 tokens per session scan A 8a3dc9ae773f
helm-router is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,138 once invoked, about $0.0003 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-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…