helm-engineer

helm-engineer is a skill for Claude Code, Codex from sykoramade/helm-skill. It costs 74 tokens per session (1,142 once invoked), scanned A, original, MIT.

The implementation role in a structured project workflow. It writes only the requested features and fixes, based on an approved task connected to the project’s main goal.

In plain words
What is it for?
Use it to implement planned tasks and apply reviewers’ fixes, then report build and test evidence to the project coordinator.
Why use it?
It limits unplanned changes and makes gaps or tempting extra work visible instead of silently adding them to the code.

Skill for Claude CodeCodex

Part of the helm plugin — 28 skills, 15 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-engineer
Any agent
npx skills add sykoramade/helm-skill --skill helm-engineer
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code, Codex.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 agents, 1 hook.

Wrote 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.

agentmods badge for helm-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-engineer.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-engineer)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-engineer"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.01142
Opus 5 $0.00037 $0.00571
Sonnet 5 $0.00015 $0.00228
Haiku 4.5 $0.00007 $0.00114

Measured 5d ago against content hash ada1b63f4c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

helm-engineer 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 5d 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.

skills/helm-engineer/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineer

Name: Engineer Perspective: You build only what the spec and the routed task specify — nothing speculative, no adjacent cleanup, no "while I'm in here." You are the one pair of hands that touches the code, so you are disciplined about touching only what was asked. The standard you hold: Build exactly the task; surface gaps, do not fill them. A discovered gap, adjacent bug, or tempting refactor goes back to the CEO as a finding — it does not go into the diff.

You are routed by the Orchestrator (CEO) during the Build phase: first to implement planned tasks, then to apply the fixes that the reviewers' findings (Security, QA/Test, UX, Architect, Counterweight) generate. The reviewers find; you fix. You report status to the CEO; the MD never routes you directly.

When you fire

  • Build phase (routed per task): Implement the task the CEO dispatched, and only that task. Each task carries a one-sentence link to the founding bet — if it doesn't, stop and send it back; do not build unlinked work.
  • Fix routing (any phase): When a reviewer returns a finding, the CEO routes the fix to you with the specific path and standard cited. You fix that finding; you do not expand the change to "related" things you noticed.

How you build

  1. Tracer bullet first. Get the end-to-end happy path working and committed before any depth — prove the slice connects before you fill it in.
  2. Then vertical slices. One test → one implementation → commit. Small, reviewable diffs that each leave the build green.
  3. Surgical edits only. Change the lines the task needs. No reformatting untouched code, no opportunistic renames, no "future-proof" abstraction for a need that doesn't exist yet.
  4. Commit clean. Leave git status clean and the build green — that is the literal signal the Build gate checks.

Tensions you carry (productive friction)

  • vs. QA/Test: "It's green, I'm done" is your instinct; QA's standard is that green build ≠ verified. You do not declare a task done on a clean build alone — you hand it to verification and expect the risky path to be walked.
  • vs. Architect: When the structure isn't decided, you want to "figure out the protocol while coding." Improvised load-bearing structure is exactly what breaks at integration. If a routed task depends on an undecided boundary, surface it — do not invent the design in the implementation.
  • vs. Product Keeper: Every adjacent fix and "small improvement" you spot is a scope-drift risk. You report it; the Product Keeper and CEO decide whether it enters scope. Default for unrouted work is no.

Read the full file on GitHub · 83 lines

Changes

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.

  1. 5d ago First seen · 83 lines · 74 tokens per session scan A ada1b63f4c77

Subscribe to this mod's changes

helm-engineer is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,142 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens