cco-shield

cco-shield is a skill for Claude Code from egorfedorov/claude-context-optimizer. It costs 23 tokens per session (386 once invoked), scanned A, original, MIT.

A status and history report for ContextShield, a protection mechanism that warns before repeatedly wasteful file reads and can create ignore rules.

In plain words
What is it for?
Use it to review protected files, estimated tokens saved and files often used together, or to suggest and apply .contextignore patterns.
Why use it?
It helps prevent the same files from being read unnecessarily across sessions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-context-optimizer plugin — 22 skills, 1 agent, 6 hooks shipped together

Good fit Use it to review protected files, estimated tokens saved and files often used together, or to suggest and apply .contextignore patterns.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add egorfedorov/claude-context-optimizer
Claude Code
/plugin install claude-context-optimizer

Made for: Claude Code.

Or install claude-context-optimizer, the plugin that ships this one along with the rest of its 22 skills, 1 agent, 6 hooks.

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 cco-shield

README.md
[![agentmods](https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/cco-shield.svg)](https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/cco-shield)
Your own site
<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/cco-shield"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/cco-shield.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 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 $0.00023 $0.00386
Opus 5 $0.00012 $0.00193
Sonnet 5 $0.00005 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 8d ago against content hash f444894d6d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cco-shield 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 8d 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.

skills/cco-shield/SKILL.md · 48 lines

What it actually says

ContextShield Status

Show the user the current ContextShield protection status and historical waste prevention stats.

Subcommands

If the user asked for suggestions (/cco-shield suggest) or to apply them (/cco-shield apply), run instead:

node ${CLAUDE_PLUGIN_ROOT}/src/context-shield.js suggest   # preview .contextignore candidates
node ${CLAUDE_PLUGIN_ROOT}/src/context-shield.js apply     # append them to ./.contextignore

suggest lists files wasted in 3+ sessions as ready-to-use .contextignore patterns with per-session token savings. apply appends them (deduped against existing rules) so those reads are blocked permanently. Show the output as-is.

Status report (default)

Run the following command to get pattern data:

node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js patterns

From the patterns data, present:

  1. ContextShield Status: Active (it's always active as a PreToolUse hook)
  2. Protected Files: List files with 3+ waste sessions — these trigger warnings before Read
  3. Tokens Saved: Estimate based on waste history (files that would have been read without shield)
  4. Co-occurrence Groups: Files that are usually edited together

Format as a clean status report. If no pattern data exists yet, tell the user: "ContextShield is warming up! It learns from your usage patterns and will start giving you smart suggestions after a few sessions."

End the report with:

ContextShield runs automatically on every Read. No configuration needed.
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. 8d ago First seen · 48 lines · 23 tokens per session scan A f444894d6d67

Subscribe to this mod's changes

cco-shield is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (107 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 386 once invoked, about $0.0001 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 2026-08-30.