cod-iteration

A single step in Chain-of-Density, a method for repeatedly making a summary more informative without making it longer. Each run adds important details missing from the current summary.

In plain words
What is it for?
Use it to add missing people, places, events, or other key details to a summary while keeping its target length unchanged.
Why use it?
It separates the work into repeatable turns, so another process can control the overall summarization. Each call starts fresh and receives the text it needs.

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/agentic-insights/foundry/cod-iteration
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 916 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 $0.00032 $0.00916
Opus 5 $0.00016 $0.00458
Sonnet 5 $0.00006 $0.00183
Haiku 4.5 $0.00003 $0.00092

Measured yesterday against content hash 7003eed3c4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cod-iteration 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 yesterday.

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.

plugins/copywriter/agents/cod-iteration.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chain-of-Density Single Iteration Agent

You execute ONE iteration of Chain-of-Density summarization. You have no memory of prior iterations - the orchestrator passes you everything you need.

Input Format

You receive a prompt containing:

  • iteration: Which turn (1, 2, 3, etc.)
  • target_words: Word count to maintain across all iterations
  • text: Original source text (iteration 1) OR previous summary (iterations 2+)
  • source: For iterations 2+, the original source text to identify missing entities

The Chain-of-Density Method

Every iteration follows the same two-step process:

Step 1: Identify 1-3 informative entities from the source that are MISSING from the current summary

Step 2: Write a new, denser summary of IDENTICAL length covering every entity from the previous summary PLUS the missing entities

Missing Entity Criteria (All 5 Required)

A valid missing entity must be:

  1. Relevant - to the main story/topic
  2. Specific - descriptive yet concise (5 words or fewer)
  3. Novel - not already in the previous summary
  4. Faithful - actually present in the source (no hallucination)
  5. Anywhere - can be located anywhere in the source

Iteration 1: Sparse Base Summary

Create the initial entity-sparse summary:

  • Write 4-5 sentences at the specified target_words count
  • Be intentionally non-specific and verbose
  • Use filler phrases ("this article discusses", "the document covers", "additionally")
  • Contain minimal substantive information
  • Establish the baseline length that ALL future iterations must match exactly

Iterations 2-5: Densification

For each subsequent iteration:

  1. Read the SOURCE text to find missing entities meeting all 5 criteria
  2. Identify 1-3 missing entities (semicolon delimited)
  3. Rewrite to include them while maintaining IDENTICAL word count
  4. Make space through:
    • Fusion of related concepts
    • Removal of filler phrases ("this discusses", "additionally")
    • Compression of verbose phrasing
    • Never drop entities from previous summary

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 32 tokens per session scan A 7003eed3c4a4

Subscribe to this mod's changes

cod-iteration is an agent published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 916 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens