What is audit-context?

A command for examining a plugin or plan for inefficient use of conversation context. It maps how information moves through the target and reports possible waste and rule violations.

Auditing a detected plugin or plan, identifying context-flow problems, checking Four Laws violations, estimating wasted tokens, and producing an audit report.

It helps reveal when a plugin or plan loads too much information, handles context poorly, or breaks the project’s context-management rules.

audit-context — Command for Claude Code by abossenbroek

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/abossenbroek/abossenbroek-claude-plugins

Made for: Claude Code.

Or install context-engineering, the plugin that ships this one along with the rest of its 1 skill, 4 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/abossenbroek/abossenbroek-claude-plugins/audit-context/github.svg)](https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/audit-context)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/audit-context"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/audit-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 625 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	$0.00000	$0.00625
Opus 5.5	$0.00000	$0.00250
Sonnet 5.5	$0.00000	$0.00125
Haiku 4.5	$0.00000	$0.00063

Measured 2mo ago against content hash 515b1051fa71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-context 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 2mo 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.

context-engineering/commands/audit-context.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-context Command

Audit a plugin or plan for context management inefficiencies.

Usage

/audit-context [path]

Arguments

path (optional):

Path to plugin directory or plan file (default: auto-detect plugin in workspace)

Instructions

You are the MINIMAL entry point for context auditing. Your ONLY job is to:

Determine the audit target
Launch the audit-coordinator agent
Return the coordinator's output directly

Step 1: Determine Target

If no path provided:

Look for .claude-plugin/plugin.json in workspace
If not found, look for recent plans in .claude/plans/
If nothing found, ask user to specify

Determine if target is a plugin or plan based on structure.

Step 2: Launch Coordinator

Use the Task tool to launch the audit-coordinator agent:

Task: Audit context management
Agent: agents/audit-coordinator.md
Prompt:
  target_path: [resolved path]
  target_type: plugin|plan

The coordinator will:

Analyze the target structure
Map context flows
Identify Four Laws violations
Calculate token waste estimates
Generate comprehensive audit report

Step 3: Return Output

Return the coordinator's audit report DIRECTLY to the user.

DO NOT:

Add commentary about the process
Explain what the coordinator did
Include intermediate analysis
Modify the report

ONLY return the final audit report.

Context Isolation Rules

This command is the FIREWALL between main session and audit work:

Main session context stays CLEAN
Only target path passes to coordinator
Only the final audit report returns to user
No intermediate analysis enters main context

Examples

/audit-context
# Audits auto-detected plugin in workspace

/audit-context ./red-agent
# Audits specific plugin directory

/audit-context ~/.claude/plans/my-plan.md
# Audits specific plan file

What Gets Audited

Four Laws Compliance

Law	Audit Check
Selective Projection	Are full snapshots passed unnecessarily?
Tiered Fidelity	Do agents have appropriate tier specs?
Reference vs Embedding	Is large data embedded instead of referenced?
Lazy Loading	Is data loaded upfront when not needed?

Read the full file on GitHub · 117 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.

2mo ago First seen · 117 lines · 0 tokens per session scan A 515b1051fa71

Subscribe to this mod's changes

audit-context is a command published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 6mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 625 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 2026-08-31.

Memory and context

audit-context next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
audit-contextabossenbroek/abossenbroek-claude-plugins	Command	2	6mo ago	BSD-3-Clause	A	0	Claude Code
minutes-ideassilverstein/minutes	Command	1.6k	yesterday	MIT	A	48	Claude Code, OpenCode
learnReflexioAI/claude-smart	Command	792	today	Apache-2.0	A	14	Claude Code
memory-storeverygoodplugins/mcp-automem	Command	66	yesterday	MIT	A	10	Claude Code
cc-memoryTheLobbi/claude	Command	21	8d ago	MIT	A	0	Claude Code
analyze-contextRohiRIK/OpenLtm	Command	29	9d ago	MIT	A	39	Claude Code
lians-recallLians-ai/Lians	Command	17	5d ago	Apache-2.0	A	19	Claude Code