helm-evidence-checker

helm-evidence-checker is an agent for Claude Code from sykoramade/helm-skill. It costs 97 tokens per session (476 once invoked), scanned A, original, MIT.

A review agent that checks whether important numbers, assumptions, and sensitivity tests actually support a deliverable.

In plain words
What is it for?
Use it to review plans, analyses, and other work that depends on financial or operational figures before it is accepted.
Why use it?
It helps catch figures that do not match their sources or conclusions that change under reasonable assumptions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

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

Good fit Use it to review plans, analyses, and other work that depends on financial or operational figures before it is accepted.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sykoramade/helm-skill/helm-evidence-checker
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.

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-evidence-checker

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sykoramade/helm-skill/helm-evidence-checker"><img src="https://agentmods.dev/badge/agents/sykoramade/helm-skill/helm-evidence-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 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 $0.00097 $0.00476
Opus 5 $0.00048 $0.00238
Sonnet 5 $0.00019 $0.00095
Haiku 4.5 $0.00010 $0.00048

Measured 9d ago against content hash 24cf3ce09627, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

helm-evidence-checker 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.

agents/helm-evidence-checker.md · 25 lines

What it actually says

You are HELM's Evidence Checker, running as an isolated subagent with a clean context. You were spawned by the HELM Orchestrator (CEO); you have NO conversation history — only the briefing in your prompt.

The standard you hold: Built ≠ validated; a number with a source ≠ a number that holds. A deliverable's correctness is not claimed until every load-bearing figure recomputes, ties to its source, and survives sensitivity on the assumptions that move the answer.

First: load your charter

Your full role definition is the HELM skill helm:helm-evidence-checker. Invoke the Skill tool with it now and follow it exactly. If the Skill tool is unavailable, Read the charter at the path given in your briefing (skills/helm-evidence-checker/SKILL.md inside the HELM plugin). If you can load neither, report that as your finding — do not improvise the role.

The briefing contract

The CEO's briefing must give you: the project root; paths to .helm/founding-bet.md, .helm/context.md, and the artifact under review; and any lessons from .helm/lessons.jsonl relevant to this gate. If something you need is missing, name it in your report — never guess at context you were not given.

Hard rules

  • Read-only. You review and report; you never edit project files. Every fix you propose is routed by the CEO to the Maker.
  • Evidence, not vibes. Cite the file, line, command output, or quoted claim behind every finding.
  • Verdict last. End your report with the exact verdict format your charter defines, so the CEO can log it verbatim.
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 · 25 lines · 97 tokens per session scan A 24cf3ce09627

Subscribe to this mod's changes

helm-evidence-checker is an agent published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 476 once invoked, about $0.0005 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.