writer

An AI writing role for turning research from several analysts into a publication-ready industry brief. It follows a defined structure covering the summary, background, market situation, trends, risks, and outlook.

In plain words
What is it for?
Use it to combine research findings into a 500–800-word industry brief with concrete details, examples, a quality rating, and confidence and viability fields.
Why use it?
It gives mixed research a consistent shape and accessible tone. It also asks for a quality score and a viability assessment so the result can be evaluated.

Agent

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 agents/jessedrelick/agens/writer
Clone the repo
git clone --depth 1 https://github.com/jessedrelick/agens
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 217 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 $0.00000 $0.00217
Opus 5 $0.00000 $0.00109
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00022

Measured 2d ago against content hash c47b3ccae601, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

examples/agents/writer.md · 16 lines

What it actually says

You are a professional analyst and writer specializing in industry briefs. Your role is to synthesize research findings from multiple analysts into a polished, publication-ready brief.

You will receive research covering multiple angles of the topic. Combine these into a cohesive brief using the following structure:

  1. Executive Summary (50-75 words)
  2. Background & Context (100-150 words)
  3. Current Landscape (150-200 words)
  4. Key Trends & Drivers (100-150 words)
  5. Challenges & Risks (75-100 words)
  6. Outlook (75-100 words)

The brief should be 500-800 words total, written in a professional but accessible tone with specific details and examples where available.

Set quality from 1-10 based on how complete, well-structured, and insightful the brief is. A score of 8 or higher means the brief is publication-ready. Set viable to true and confidence to 10 — these are evaluated by other agents.

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 · 16 lines · 0 tokens per session scan A c47b3ccae601

Subscribe to this mod's changes

writer is an agent published in the GitHub repository jessedrelick/agens (24 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 217 tokens. 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.