helix.mcp: Skill for Claude Code

.squad/skills/helix-sdk-summary-vs-details/SKILL.md

helix-sdk-summary-vs-details is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 36 tokens per session (1,039 once invoked), scanned A, original, MIT.

An audit method for comparing fields returned by Helix's work-item list response with fields returned by its per-item details response. Helix is a system that runs and reports build or test work.

In plain words
What is it for?
Reviewing each DetailsAsync call, matching the fields it reads against WorkItemSummary, and deciding safely whether that call can be removed after an SDK update.
Why use it?
It identifies when repeated details requests are no longer needed because the list response already contains the required fields, reducing one network request per work item.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is lewing/helix.mcp's own configuration. It tells Claude Code and Codex how to work on helix.mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything helix.mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lewing/helix.mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lewing/helix.mcp/main/.squad/skills/helix-sdk-summary-vs-details/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lewing/helix.mcp

Made for: Claude Code, Codex.

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 helix-sdk-summary-vs-details

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewing/helix.mcp/helix-sdk-summary-vs-details/github.svg)](https://agentmods.dev/skills/lewing/helix.mcp/helix-sdk-summary-vs-details)
Your own site
<a href="https://agentmods.dev/skills/lewing/helix.mcp/helix-sdk-summary-vs-details"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/helix-sdk-summary-vs-details/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.

agentmods 80×15 button for helix-sdk-summary-vs-details

Your own site · 80×15
<a href="https://agentmods.dev/skills/lewing/helix.mcp/helix-sdk-summary-vs-details"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/helix-sdk-summary-vs-details.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.01039
Opus 5 $0.00018 $0.00519
Sonnet 5 $0.00007 $0.00208
Haiku 4.5 $0.00004 $0.00104

Measured 11d ago against content hash 9d77d6ed7672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

helix-sdk-summary-vs-details 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 11d 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.

.squad/skills/helix-sdk-summary-vs-details/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Helix SDK: WorkItemSummary vs. WorkItemDetails Field Surface

Use this pattern when a Helix.Client SDK bump potentially adds new fields to WorkItemSummary (the list-API response), and you need to decide which DetailsAsync (per-item) call sites can be eliminated.

The optimization problem

ListAsync returns a WorkItemSummary for every work item in one HTTP call.
DetailsAsync fetches WorkItemDetails per work item — O(N) HTTP calls.

When the list API starts returning fields that previously required a per-item details call, those details calls become unnecessary (for those fields). The key question: which fields does each call site actually need?

Audit checklist (run after each SDK bump)

For every call site that calls GetWorkItemDetailsAsync:

  1. List the fields read from details.
    Common: ExitCode, State, MachineName, Started, Finished, ConsoleOutputUri.

  2. Check which of those fields are now on IWorkItemSummary.
    After arcade PR #16722 (client ≥ 11.0.0-beta.26325.x): ExitCode, ConsoleOutputUri.

  3. Decision matrix:

Fields needed from details Can skip DetailsAsync?
ONLY ExitCode ✅ Use summary.ExitCode
ONLY ConsoleOutputUri ✅ Use summary.ConsoleOutputUri
ONLY ExitCode + ConsoleOutputUri ✅ Use both from summary
State or MachineName or Started/Finished (duration) ❌ Keep DetailsAsync
  1. For loop/batch callers (N work items): Only skip DetailsAsync for the whole batch if NONE of the loop iterations need State/MachineName/Duration. A hybrid is also valid: use summary.ExitCode to avoid DetailsAsync for zero-exit-code items, still call it for non-zero/null.

The ExitCode=0 fast-path (canonical optimization)

// In a loop over IWorkItemSummary items:
var tasks = workItems.Select(wi => wi.ExitCode == 0
    ? Task.FromResult(CreatePassedResult(wi, id))   // skip DetailsAsync
    : CreateDetailedResultAsync(wi, id, semaphore, ct)) // still calls DetailsAsync
    .ToList();

Read the full file on GitHub · 81 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. 11d ago First seen · 81 lines · 36 tokens per session scan A 9d77d6ed7672

Subscribe to this mod's changes

helix-sdk-summary-vs-details is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,039 once invoked, about $0.0002 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

review

Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".

anton-abyzov/specweave · 43 tokens

sw-review

Adversarial fresh-context review of an increment before it ships; every finding cites path:line and is re-verified. Use for "review this", "critique the implementation", "review before closing".

anton-abyzov/specweave · 42 tokens

argot-setup

Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…

get-tmonier/argot · 129 tokens

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens

argot-write-rule

Codify a repo convention argot's built-ins don't cover into a scripted custom rule — a .argot/rules/NAME/rule.toml manifest plus a sandboxed Rhai script that fires exactly like a built-in, gated on a green fixture suite before it ever sees a real diff. Use when the user asks to "write an argot rule for X", "codify…

get-tmonier/argot · 131 tokens

argot-refresh

Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…

get-tmonier/argot · 136 tokens