A command for cleaning up stored context by removing duplicate entries and identifying older entries replaced by newer ones. It proposes a plan first and applies changes only after approval.

Use it to review terminology, principles, and recurring guidance for duplicates, conflicts, or outdated versions before consolidating them.

It helps keep project context shorter and less contradictory, so later work is based on clearer information.

consolidate — Command for Claude Code by extremeclarity

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/extremeclarity/claude-plugins

Made for: Claude Code.

Or install worldview, the plugin that ships this one along with the rest of its 5 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/extremeclarity/claude-plugins/consolidate.svg)](https://agentmods.dev/commands/extremeclarity/claude-plugins/consolidate)

Your own site

<a href="https://agentmods.dev/commands/extremeclarity/claude-plugins/consolidate"><img src="https://agentmods.dev/badge/commands/extremeclarity/claude-plugins/consolidate.svg" alt="Measured on agentmods" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 495 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.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.00495
Opus 5	$0.00004	$0.00247
Sonnet 5	$0.00002	$0.00099
Haiku 4.5	$0.00001	$0.00049

Measured 6d ago against content hash b31d12a5727e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

consolidate 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.

plugins/worldview/commands/consolidate.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consolidate

Remove redundant entries and merge overlapping context.

Execution Model

Silent execution: Do not narrate your reasoning process. Work through steps 1-4 internally, then output only the final plan in step 5.

Enter plan mode
Read — Load all context files and framework index
Plan — Analyze for redundancy and supersession using rules below
Deep read — If potential framework overlaps detected from index, read the full framework files before making recommendations
Present — Show only the final plan to user for approval (no preamble, no reasoning)
Execute — Apply approved changes

What to Look For

Redundant Entries

Two entries express the same idea. Propose:

Merge — combine into a single, stronger entry
Remove — delete the weaker/duplicate entry

Superseded Entries

Newer entry contradicts or replaces older one. Propose:

Remove — delete the stale version

Targets

Terminology

Same term defined differently across entries
Different terms meaning the same thing

Principles

Conflicting guidance (newer supersedes older)
Same principle restated in different words

Anti-patterns

Duplicate warnings
Overlapping anti-patterns that could merge

Insights

Newer insight invalidates older one
Same insight captured multiple times

Frameworks

Scan index for potential overlaps (similar problem types, related summaries)
If potential overlaps found, read full framework files to confirm before recommending
Only propose merge/removal after reading actual content

Plan Format

Present proposed changes grouped by action:

## Remove
- [category] "entry text" — reason

## Merge
- [category] "entry A" + "entry B" → "merged entry"

Anti-Patterns

DO NOT narrate your analysis — work silently, output only the final plan
DO NOT remove entries that are merely related — they must be truly redundant or superseded
DO NOT skip plan mode — all changes require approval
DO NOT auto-merge without showing both originals and proposed result
DO NOT recommend framework changes based only on index summaries — read full files first

Read the full file on GitHub · 83 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.

6d ago First seen · 83 lines · 8 tokens per session scan A b31d12a5727e

Subscribe to this mod's changes

consolidate is a command published in the GitHub repository extremeclarity/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 495 once invoked, about $0.0000 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.

Memory and context

consolidate