Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns

MITAuto-check passedAI & LLM Engineering

Install Cco Pack

skills CLI
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-pack -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install egorfedorov/claude-context-optimizer cco-pack --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cco-pack .claude/skills/cco-pack && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cco-pack
GitHub stars
114
Token cost
~448 tokens
SKILL.md length
205 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns

  • Works in 4 steps: Mentioned in prompt — explicit file… → Modified in git working tree → 85 → Historically useful in this project… → …
  • Tasks that involve LLM cost and token optimization
  • SKILL.md covers How to use, How it ranks files, Token budget awareness and Presentation
  • Calls node

What it does

Cco Pack is an agent skill from egorfedorov/claude-context-optimizer. Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns

Its SKILL.md is about 450 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM cost and token optimization. It works with Git. The repository describes itself as: Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware… The licence is MIT.

When your agent uses it

  • Tasks that involve LLM cost and token optimization

Example prompts

  • “/cco-pack”

Requirements

  • Pre-approved tools (allowed-tools): Bash(node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js:*), Read

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Mentioned in prompt — explicit file paths or recognisable names → relevance 100
  2. Modified in git working tree → 85
  3. Historically useful in this project (high confidence, edited often) → up to 70
  4. Keyword match against the task → up to 70

What it can do on your machine

Read from SKILL.md and the folder at commit f6f20ee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js:*)
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cco Pack loads about 448 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 205 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~448

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from egorfedorov/claude-context-optimizer at commit f6f20ee, republished under its MIT licence (© egorfedorov). 205 words, ~448 tokens.

Download SKILL.mdSave it as .claude/skills/cco-pack/SKILL.md (or your agent's skills folder).
name
cco-pack
description
Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns
allowed-tools
Bash(node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js:*), Read
license
MIT

Smart Context Pack

When the user runs /cco-pack or asks "what files do I need for X", build a curated, token-budget-aware list of files to load instead of guessing or reading the whole repo.

How to use

bash
node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js "the task description"

Or for the current git state without a description:

bash
node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js

Or to feed it back into automation as JSON:

bash
node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js --json "..."

How it ranks files

Priority order:

  1. Mentioned in prompt — explicit file paths or recognisable names → relevance 100
  2. Modified in git working tree → 85
  3. Historically useful in this project (high confidence, edited often) → up to 70
  4. Keyword match against the task → up to 70

For each file the pack also suggests offset / limit — pointing at the structurally relevant section based on file landmarks (function/class declarations near task keywords).

Token budget awareness

Pack stops adding files once it would exceed 25% of the user's effective context budget. The budget itself respects the configured model (e.g. the full 1M window for opus-5.5 — 1M is standard on Opus, no premium tier).

Presentation

After running, present the list to the user and offer to:

  • Read the top N files with the suggested offset/limit
  • Save the set as a template (/cco-templates create <name>)
  • Drop low-relevance items if they want a tighter pack

© egorfedorov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/cco-pack of egorfedorov/claude-context-optimizer.

Open the folder on GitHubat commit f6f20ee

Compare with similar skills

Cco Pack next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cco Pack compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cco Pack this skillegorfedorov/claude-context-optimizer114—~448Automated safety check: PassMIT
Vibepcx-wave/vibe-skill120—~7.2kAutomated safety check: NotesMIT
Levyra Context EfficiencyLUC4N3X/Levyra-deepsound533—~1.3kAutomated safety check: NotesGPL-3.0
Context Compressionguanyang/open-agent-hub9772 repos~4.6kAutomated safety check: PassMIT
Bounty Hunter1sadjlk/bounty-hunter-skill2821 repos~761Automated safety check: PassMIT
Skill Shortenerluongnv89/asm954—~3.8kAutomated safety check: NotesMIT

Similar skills

  • Vibe

    pcx-wave/vibe-skill

    Delegate a coding task to Mistral Vibe and supervise the result via git diff.

    120 GitHub stars~7.2k tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check: notes
  • Levyra Context Efficiency

    LUC4N3X/Levyra-deepsound

    A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…

    533 GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check: notes
  • Context Compression

    guanyang/open-agent-hub

    This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…

    977 GitHub starsUsed in 2 repos~4.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Bounty Hunter

    1sadjlk/bounty-hunter-skill

    A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.

    282 GitHub starsUsed in 1 repo~761 tokens
    AI & LLM EngineeringAuto-check passed
  • Skill Shortener

    luongnv89/asm

    Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.

    954 GitHub stars~3.8k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes
  • Codebase Cost Estimate

    jbarbier/claude-code-cost-estimate

    Estimates what a codebase would cost a traditional human team to rebuild, with P10, P50 and P90 ranges cross-checked by COCOMO II, Function Points and LOCOMO.

    111 GitHub stars~5k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

More from egorfedorov/claude-context-optimizer

All 13 skills in this repo
  • Smart Loader

    egorfedorov/claude-context-optimizer

    Automatically suggests optimal files to preload based on the user's task description and historical context patterns.

    114 GitHub stars~530 tokensUpdated 9 days ago
    Auto-check passed
  • Cco

    egorfedorov/claude-context-optimizer

    Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions

    114 GitHub stars~465 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Budget

    egorfedorov/claude-context-optimizer

    Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5.5 default fallback, full 1M context at standard price)

    114 GitHub stars~808 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Config

    egorfedorov/claude-context-optimizer

    View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap

    114 GitHub stars~839 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Patterns

    egorfedorov/claude-context-optimizer

    Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one

    114 GitHub stars~665 tokensUpdated 9 days ago
    Auto-check passed
  • Cco Shield

    egorfedorov/claude-context-optimizer

    Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste

    114 GitHub stars~457 tokensUpdated 9 days ago
    Auto-check passed

Works with

Questions about Cco Pack

What does Cco Pack do?

Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns. Cco Pack is an agent skill from egorfedorov/claude-context-optimizer.

When should I use Cco Pack?

Cco Pack fits situations like: tasks that involve LLM cost and token optimization.

How do I install Cco Pack in Claude Code?

Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-pack -a claude-code`. Or copy the skill folder (skills/cco-pack in egorfedorov/claude-context-optimizer) into .claude/skills/cco-pack in your project. Claude Code loads it when a task matches its description.

How do I install Cco Pack in Codex?

Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-pack -a codex`. Or copy the skill folder (skills/cco-pack in egorfedorov/claude-context-optimizer) into .agents/skills/cco-pack in your project. Codex loads it when a task matches its description.

Can I use Cco Pack in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add egorfedorov/claude-context-optimizer --skill cco-pack -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cco-pack, .gemini/skills/cco-pack, .github/skills/cco-pack and .opencode/skills/cco-pack in your project.

What does Cco Pack need to run?

Going by SKILL.md and its folder, Cco Pack needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Bash(node ${CLAUDE_PLUGIN_ROOT}/src/smart-pack.js:*), Read.

Does Cco Pack access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cco Pack safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cco Pack use?

Cco Pack is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cco Pack use?

About 448 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cco Pack?

Skills that share tags, products or a category with Cco Pack: Vibe (pcx-wave/vibe-skill, 120 stars), Levyra Context Efficiency (LUC4N3X/Levyra-deepsound, 533 stars), Context Compression (guanyang/open-agent-hub, 977 stars) and Bounty Hunter (1sadjlk/bounty-hunter-skill, 282 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cco Pack?

egorfedorov (a GitHub user) maintains it in egorfedorov/claude-context-optimizer, which has 114 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 30, 2026.

Source: egorfedorov/claude-context-optimizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.