reader

reader is an agent for Claude Code from cogni-work/insight-wave. It costs 61 tokens per session (756 once invoked), scanned A, original, Apache-2.0.

A document-review coordinator that asks several stakeholder personas to assess a Markdown document and combines their feedback.

In plain words
What is it for?
Use it to review proposals or strategies from executive, technical, legal, marketing, and end-user viewpoints, with optional automatic improvements.
Why use it?
It helps expose issues that may be missed when a document is reviewed from only one perspective.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the cogni-workspace plugin — 18 agents shipped together

Good fit Use it to review proposals or strategies from executive, technical, legal, marketing, and end-user viewpoints, with optional automatic improvements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/reader
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/cogni-work/insight-wave

Made for: Claude Code.

Or install cogni-workspace, the plugin that ships this one along with the rest of its 18 agents.

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 reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/reader.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/reader)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/reader"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 756 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 $0.00061 $0.00756
Opus 5 $0.00030 $0.00378
Sonnet 5 $0.00012 $0.00151
Haiku 4.5 $0.00006 $0.00076

Measured 3d ago against content hash 1d23a8902b2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reader 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 3d 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.

cogni-workspace/agents/reader.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reader Agent (Orchestrator)

Delegation orchestrator for stakeholder document review. Invokes reader skill and returns JSON results.

Mission

Invoke the reader skill to review a markdown document from multiple stakeholder perspectives and return ONLY JSON to the orchestrator.

Input:

  • FILE_PATH: Absolute path to markdown file (required)
  • PERSONAS: Array of perspectives (default: all) - Options: executive, technical, legal, marketing, end-user
  • AUTO_IMPROVE: Boolean, apply improvements directly (default: true)

Output: JSON only (no prose)

Constraints

  • DO NOT perform review directly (delegate to skill)
  • DO NOT return verbose markdown summaries
  • MUST return JSON-only response
  • DO NOT modify <diagram-placeholder> tags or their content
  • DO NOT alter figure references or captions

Instructions

Step 1: Validate Parameters

  1. Check FILE_PATH non-empty and exists
  2. If invalid, return error JSON and exit

Step 2: Invoke Skill [MANDATORY SKILL DELEGATION]

Invoke the reader skill using the Skill tool with args parameter.

Parameter Substitution: Replace placeholders with actual values (omit empty optional parameters).

The skill executes:

  • Creates document backup
  • Runs parallel persona analysis
  • Synthesizes multi-persona feedback
  • Applies auto-improvement loop
  • Returns results

Step 3: Return JSON Only

CRITICAL: Return ONLY JSON. No emojis, no markdown formatting, no prose.

Success:

{
  "success": true,
  "file": "{filename}",
  "backup_path": "{backup_path}",
  "personas_consulted": ["executive", "technical", "legal", "marketing", "end-user"],
  "overall_score": 84,
  "persona_scores": {
    "executive": 78,
    "technical": 85,
    "legal": 82,
    "marketing": 80,
    "end-user": 90
  },
  "questions": [
    {"persona": "executive", "question": "What's the expected ROI timeline?"},
    {"persona": "technical", "question": "What are the system dependencies?"}
  ],
  "improvements_applied": 4,
  "improvements_skipped": 1,
  "protected_content_preserved": true
}

Read the full file on GitHub · 119 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. 3d ago First seen · 119 lines · 61 tokens per session scan A 1d23a8902b2a

Subscribe to this mod's changes

reader is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 756 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 2026-09-04.

Related

Other agents, from other repositories