agentmods.dev

context-compress-audit

context-compress-audit is a skill for Claude Code, Codex from Open330/context-compress. It costs 70 tokens per session (468 once invoked), scanned A, original, MIT.

A repository and agent-session audit that finds large raw outputs entering the agent’s context without being compressed or indexed.

In plain words
What is it for?
Use it to find risky output handling in plugin files, hooks, setup files, documentation, and examples, then identify where compressed or searchable workflows should be used.
Why use it?
Unfiltered command, file, web, and MCP output can waste context space and make sessions harder to manage.

Skill for Claude CodeCodex

Part of the context-compress plugin — 4 skills, 1 MCP server shipped together

not rated 2 7d ago A scan 70 tokens original MIT
View the source file Open330/context-compress
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 skills/open330/context-compress/context-compress-audit
Any agent
npx skills add Open330/context-compress --skill context-compress-audit
Clone the repo
git clone --depth 1 https://github.com/Open330/context-compress

Made for: Claude Code, Codex.

Or install context-compress, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 context-compress-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/open330/context-compress/context-compress-audit.svg)](https://agentmods.dev/skills/open330/context-compress/context-compress-audit)
Your own site
<a href="https://agentmods.dev/skills/open330/context-compress/context-compress-audit"><img src="https://agentmods.dev/badge/skills/open330/context-compress/context-compress-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.00468
Opus 5 $0.00035 $0.00234
Sonnet 5 $0.00014 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 4d ago against content hash 74d8518cda90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-compress-audit scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `Bash` for tests, logs, `git log`, `git diff`, `curl`, `kubectl`, `docker`, `npm test`
skills/context-compress-audit/SKILL.md · 50 lines

What it actually says

Context-Compress Audit

Find places where large raw output can still enter the agent context window.

Procedure

  1. Run mcp__context-compress__stats first if the tool is available.
  2. Inspect setup surfaces that control routing:
    • .codex-plugin/plugin.json
    • .claude-plugin/plugin.json
    • .mcp.json
    • hooks/
    • skills/
    • README install instructions
  3. Search for risky guidance or examples that encourage raw output:
    • Bash for tests, logs, git log, git diff, curl, kubectl, docker, npm test
    • Read for large logs, bundled files, snapshots, CSV/JSON dumps
    • WebFetch for documentation pages that should use fetch_and_index
    • Playwright snapshots without a file/index/search path
  4. Report only actionable findings. Prefer one-line fixes that route work through:
    • batch_execute for several commands plus searches
    • execute for command/API output that must be analyzed first
    • execute_file for large local files
    • fetch_and_index plus search for web documentation

Output

Use this format:

## Context-Compress Audit

- [severity] file:line - raw-output risk. Replace with <tool/workflow>.
- [severity] file:line - missing install/routing coverage. Add <specific fix>.

Summary: <N> findings, estimated impact <low|medium|high>.

Severity:

  • high: large output can enter context by default.
  • medium: docs/examples teach a wasteful path.
  • low: minor wording, missing cross-link, or optional setup gap.

If nothing meaningful is found, say No raw-output waste found. Routing looks covered.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 50 lines · 70 tokens per session scan A 74d8518cda90

Subscribe to this mod's changes

context-compress-audit is a skill published in the GitHub repository Open330/context-compress (2 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 468 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsProductivityai-agentsclaude-codecontext-windowdeveloper-toolshooksmcp
Related

Other skills, from other repositories

scrim

Report what Scrim thinned from tool output and API-equivalent token mix. Use when the user runs /scrim, or asks about quota, context burn, or tool-output size.

nikshepsvn/scrim · 41 tokens

hooks-eval

Evaluate hook security, performance, and SDK compliance. Use for audits.

athola/claude-night-market · 18 tokens

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens

task-graph

Execute an approved multi-task plan as a verified DAG with @taskgraph — parallel squad workers per task, validation gates the engine runs itself, and an independent reviewer verdict before any task counts as done. Use for deliveries of 5+ tasks with real independence between them; for smaller work dispatch workers…

diillson/chatcli · 69 tokens

github

Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".

diillson/chatcli · 78 tokens

airtable

Read and write Airtable bases via the official REST API and the user's personal access token — list/filter records, create, update, delete. Use when asked to "add a row to Airtable", "find records in my base", "update this Airtable record".

diillson/chatcli · 57 tokens