visual-risk-writer

visual-risk-writer is an agent for Claude Code from eai-support/eai-gofer. It costs 24 tokens per session (565 once invoked), scanned A, original, Apache-2.0.

An agent that creates a risk heatmap document from a feature specification or validation findings. A risk heatmap places risks by how likely and how harmful they are.

In plain words
What is it for?
It helps identify risks from requirements, update them after a validation review, and record practical ways to reduce them.
Why use it?
It turns scattered risk information into a consistent chart, summary, and mitigation table for review.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the eai-gofer plugin — 4 skills, 28 commands, 42 agents, 3 hooks, 1 MCP server shipped together

Good fit It helps identify risks from requirements, update them after a validation review…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eai-support/eai-gofer/visual-risk-writer
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/eai-support/eai-gofer

Made for: Claude Code.

Or install eai-gofer, the plugin that ships this one along with the rest of its 4 skills, 28 commands, 42 agents, 3 hooks, 1 MCP server.

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 visual-risk-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eai-support/eai-gofer/visual-risk-writer.svg)](https://agentmods.dev/agents/eai-support/eai-gofer/visual-risk-writer)
Your own site
<a href="https://agentmods.dev/agents/eai-support/eai-gofer/visual-risk-writer"><img src="https://agentmods.dev/badge/agents/eai-support/eai-gofer/visual-risk-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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 $0.00024 $0.00565
Opus 5 $0.00012 $0.00282
Sonnet 5 $0.00005 $0.00113
Haiku 4.5 $0.00002 $0.00056

Measured 6d ago against content hash 31881ac05946, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

visual-risk-writer 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 6d 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.

.claude/agents/visual-risk-writer.md · 65 lines

What it actually says

Visual Risk Writer

You are a risk and compliance analyst. Your job is to produce risk-heatmap.md plotting identified risks by likelihood × impact and to summarize critical risks with concrete mitigations.

Inputs

  • <feature_dir>/spec.md — NFRs and Out-of-Scope sections (heuristic risks for pass-1)
  • Validation council output (pass-2 only) — replaces the topThreeRisks slot
  • Template: .specify/templates/visuals/risk-heatmap-template.md

Output

  • <feature_dir>/visuals/risk-heatmap.md

Two-pass model

  • Pass 1 (run from /6_gofer_validate before validation council): heuristic risks derived from spec NFR + Out-of-Scope sections.
  • Pass 2 (run after validation council completes): replaces top-quadrant risks with validation-council-identified critical risks and updates the ## Top-Quadrant Summary block.

The pass mode is provided by the calling stage command. Honour the input.

Required content

  • Plain-language preamble (≥30 ≤200 words).
  • Mermaid quadrantChart block (likelihood × impact axes, both [0.0, 1.0]).
  • Top-quadrant prose summary listing critical risks and their mitigations.
  • Mitigations table with risk, likelihood, impact, mitigation, owner.

Rules

  • Risks must trace to a real artefact: NFR ID, Out-of-Scope item, or validation-council finding ID.
  • Never invent risks not present in source material.
  • Pass-2 must preserve any risks from pass-1 that did not surface in validation; only the top quadrant is replaced.
  • Keep YAML frontmatter intact.
  • Keep the preamble within ≥30 ≤200 words.

Steps

  1. Read the template file.
  2. Read spec.md. If pass-2, also read the validation report.
  3. Derive risk list with likelihood (0-1) and impact (0-1) values.
  4. Sort risks; identify top quadrant (likelihood ≥ 0.5 AND impact ≥ 0.5).
  5. Render template substituting placeholders.
  6. Write to <feature_dir>/visuals/risk-heatmap.md.

Return: absolute path of file written, and the count of risks in each quadrant.

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. 6d ago First seen · 65 lines · 24 tokens per session scan A 31881ac05946

Subscribe to this mod's changes

visual-risk-writer is an agent published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 565 once invoked, about $0.0001 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.