brief

A tool for turning the claims collected during a research sprint into a decision brief.

In plain words
What is it for?
It helps create an HTML, PDF, or Markdown brief with a summary, findings grouped by topic, risks, mitigations, and recommendations.
Why use it?
It gathers the current findings into one checked document and flags problems that could make the brief unreliable.

Skill for Claude CodeCodex

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/grainulation/grainulator/brief
Any agent
npx skills add grainulation/grainulator --skill brief
Clone the repo
git clone --depth 1 https://github.com/grainulation/grainulator

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 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 $0.00014 $0.00649
Opus 5 $0.00007 $0.00324
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 2d ago against content hash e58caeb122a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brief 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 2d 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/brief/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/brief -- Generate a decision brief

The user wants a compiled output document from the current sprint.

Arguments

$ARGUMENTS

Optional: output format (pdf, html, md). Default: html.

Instructions

  1. Run wheat_compile to ensure compilation is current and there are no blocking conflicts.

    • If compilation fails due to unresolved conflicts, stop and suggest /resolve.
  2. Check sprint readiness via wheat_status:

    • Minimum 5 active claims to generate a meaningful brief
    • At least 2 topics covered
    • Warn if all claims are the same type (type monoculture)
  3. Read compilation.json -- this is the source of truth, never read claims.json directly for output.

  4. Read the template at ${CLAUDE_PLUGIN_ROOT}/skills/_templates/sidebar-brief.html for the canonical accessible HTML structure. All generated HTML MUST follow this template exactly. Note: the path uses ${CLAUDE_PLUGIN_ROOT} because the template lives in the Grainulator plugin directory, not the user's repo.

  5. Generate the brief using mill_convert:

    • Format: user-requested or default to HTML
    • Structure: Executive summary, key findings by topic, risks and mitigations, recommendations, evidence appendix
    • Include claim IDs as references throughout
  6. WCAG compliance checklist -- first read and apply every item from ${CLAUDE_PLUGIN_ROOT}/skills/_templates/wcag-shared.md, then verify these brief-specific items:

    • <nav aria-label="Table of contents"> wrapping sidebar links
    • aria-current="page" on active sidebar link (JS IntersectionObserver updates this)
    • Heading hierarchy: <h1> page title, <h2> sections, <h3> subsections -- never skip levels
    • All <table> elements have <caption> and <th scope="col|row">
    • Mobile sidebar uses <details><summary> disclosure, not display: none
    • Tags include text prefix (e.g., "Tested: verified"), never color alone
  7. Write output to output/brief.<ext> in the sprint directory.

Read the full file on GitHub · 67 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. 2d ago First seen · 67 lines · 14 tokens per session scan A e58caeb122a3

Subscribe to this mod's changes

brief is a skill published in the GitHub repository grainulation/grainulator (86 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 649 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 2026-08-30.