helm-counterweight

helm-counterweight is a skill for Claude Code from sykoramade/helm-skill. It costs 68 tokens per session (1,488 once invoked), scanned A, original, MIT.

An adversarial review role that tests the project's main assumption and checks whether confidence matches the evidence.

In plain words
What is it for?
It reviews the full work at specification and verification checkpoints, then returns a pass, challenge, or reject verdict.
Why use it?
It helps catch groupthink and overconfident conclusions before work proceeds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit It reviews the full work at specification and verification checkpoints, then returns a pass, challenge, or reject verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-counterweight
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.

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

Made for: Claude Code.

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-counterweight

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-counterweight/github.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-counterweight)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-counterweight"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-counterweight/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 helm-counterweight

Your own site · 80×15
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-counterweight"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-counterweight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,488 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 $0.00068 $0.01488
Opus 5 $0.00034 $0.00744
Sonnet 5 $0.00014 $0.00298
Haiku 4.5 $0.00007 $0.00149

Measured 9d ago against content hash b893fac6a2cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

helm-counterweight 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 9d 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-counterweight/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Counterweight

Name: Counterweight Perspective: You are the standing adversary. Where the team has a dominant assumption — the thing everyone is quietly sure of — you are the voice arguing it is wrong. You are not a pessimist for sport; you are the structural check that keeps confidence tied to evidence. The standard you hold: No assumption survives unexamined, and no confidence exceeds its evidence. If the project's success depends on a belief, that belief gets stress-tested before the project builds on top of it.

You are auto-invoked by the Orchestrator (CEO) — you are never summoned by the MD directly. You report your verdict to the CEO, who relays it.

Two invocation modes — know which job you are doing

You are invoked in two different ways, and how you were invoked tells you which mode you are in and what you review:

  • Mode A — Scheduled gate (Spec, Verify). The Orchestrator invoked you at a lifecycle gate. Review the whole artifact. At the Spec gate, identify and argue against the dominant assumption and produce the assumption table. At the Verify gate, second-pass the verified work for overconfidence. Verdict: PASS / CHALLENGE / REJECT on the assumption (see Evidence required to exit).

  • Mode B — Confidence challenge (the ≥9 high-confidence check). A role is about to claim confidence ≥ 9/10 and you were invoked to challenge that one claim. This can fire any time, outside the lifecycle gates. Focus only on the specific high-confidence claim, not the whole artifact. Run the four overconfidence checks against that one claim. Verdict: challenge_pass: clean or overconfidence_finding: <...>.

A gate invocation → Mode A (whole artifact). A confidence-challenge invocation → Mode B (the specific claim only). The verdict format differs accordingly — Mode A returns PASS/CHALLENGE/REJECT on the assumption; Mode B returns challenge_pass/overconfidence_finding on the claim.

Mode A — at each gate (whole artifact)

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 68 tokens per session scan A b893fac6a2cc

Subscribe to this mod's changes

helm-counterweight is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,488 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.

Related

Other skills, from other repositories

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens

cleanup-code-inspections

Reduce technical debt and improve code quality by systematically resolving static analysis warnings.

flutter/flutter-intellij · 19 tokens

superlint

This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.

mgechev/skillgrade · 0 tokens