LLM Fine Tuning
sickn33/agentic-awesome-skills
Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP.
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
MITAuto-check passed
Install Cco Config
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install egorfedorov/claude-context-optimizer cco-config --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cco-config .claude/skills/cco-config && rm -rf skills-srcUse ~/.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/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .claude/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-configType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install egorfedorov/claude-context-optimizer cco-config --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cco-config .agents/skills/cco-config && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .agents/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install egorfedorov/claude-context-optimizer cco-config --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cco-config .cursor/skills/cco-config && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .cursor/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/egorfedorov/claude-context-optimizer.git --path skills/cco-config--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install egorfedorov/claude-context-optimizer cco-config --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cco-config .gemini/skills/cco-config && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .gemini/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install egorfedorov/claude-context-optimizer cco-configInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cco-config .github/skills/cco-config && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .github/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install egorfedorov/claude-context-optimizer cco-config --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egorfedorov/claude-context-optimizer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cco-config .opencode/skills/cco-config && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cco-config" agent skill from https://github.com/egorfedorov/claude-context-optimizer/tree/main/skills/cco-config into .opencode/skills/cco-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cco-config", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cco-config- GitHub stars
- 114
- Token cost
- ~839 tokens
- SKILL.md length
- 377 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
- SKILL.md covers show (or no arguments), get, set and reset [key], plus 2 more sections
- Calls node
What it does
Cco Config is an agent skill from 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
Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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.
Example prompts
- “/cco-config”
Requirements
- Pre-approved tools (allowed-tools): Bash(node ${CLAUDE_PLUGIN_ROOT}/src/config.js:*)
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/config.js:*)
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 Config loads about 839 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 377 words of instructions outside code blocks.
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). 377 words, ~839 tokens.
Download SKILL.mdSave it as
.claude/skills/cco-config/SKILL.md (or your agent's skills folder).- name
- cco-config
- description
- View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
- allowed-tools
- Bash(node ${CLAUDE_PLUGIN_ROOT}/src/config.js:*)
- license
- MIT
- argument-hint
- [show | get <key> | set <key> <value> | reset [key]]
CCO Config — tune how aggressive the optimizer is
CCO's behavior knobs used to be magic numbers spread across four modules.
This surfaces them, range-validated, in ~/.claude-context-optimizer/config.json
under thresholds.
The plugin root is the directory containing src/config.js. Run everything
from there.
Parse $ARGUMENTS:
show (or no arguments)
node ${CLAUDE_PLUGIN_ROOT}/src/config.jsPrint the table as-is. * marks values the user set; ! marks a stored value
that failed validation and is being ignored in favour of the default. If any
! rows appear, point them out — a typo there means a knob silently isn't
doing what the user thinks.
get <key>
node ${CLAUDE_PLUGIN_ROOT}/src/config.js get <key>set <key> <value>
node ${CLAUDE_PLUGIN_ROOT}/src/config.js set <key> <value>Exits non-zero with the valid range on a bad value or unknown key — relay that message rather than guessing a correction. After a successful set, say which behavior it changes (see the table below), because the effect is not obvious from the key name alone.
reset [key]
node ${CLAUDE_PLUGIN_ROOT}/src/config.js reset <key> # one key
node ${CLAUDE_PLUGIN_ROOT}/src/config.js reset # everything back to defaultsResetting everything discards all the user's tuning — confirm first unless they were explicit ("reset all", "вернуть всё по умолчанию").
The keys
| Key | Default | What it changes |
|---|---|---|
rereadWarnAt | 3 | reads of an unedited file before the first re-read warning |
rereadEscalateAt | 5 | reads before the "put it in CLAUDE.md" escalation |
bigFileLines | 500 | full-read line count that triggers the offset/limit warning |
mediumFileLines | 200 | full-read line count that triggers the soft hint |
staleTokenRatio | 0.10 | share of budget loaded after a file before Read Cache re-allows it |
staleFiles | 8 | other files loaded after a file before it counts as evicted (at 200K) |
staleTimeMs | 600000 | ms since last read before a cached file counts as stale |
promptMinWords | 8 | word count below which the coach calls a prompt too vague |
promptIdealMaxWords | 200 | upper bound of the coach's "ideal length" band |
promptTooLongWords | 500 | word count above which the ask is considered buried |
packBudgetPercent | 25 | max share of the budget /cco-pack may consume |
Show full SKILL.md (80 more words)Show less
Tuning guidance
- Too many re-read warnings? Raise
rereadWarnAtto 4–5. - Read Cache blocking files you still need? Lower
staleTimeMs(e.g.300000= 5 min) orstaleTokenRatioso cached entries go stale sooner. - Read Cache not saving much? Raise them — entries stay fresh longer and more repeat reads get blocked.
- Working on a 1M-context model with long prompts? Raise
promptTooLongWords; the default band is tuned for shorter asks. CCO_STALE_TIME_MSin the environment still overridesstaleTimeMs, for a one-off experiment without changing config.
© 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-config of egorfedorov/claude-context-optimizer.
Open the folder on GitHubat commit f6f20ee
Compare with similar skills
Cco Config 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cco Config this skillegorfedorov/claude-context-optimizer | 114 | — | ~839 | Automated safety check: Pass | MIT | |
| LLM Fine Tuningsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Agent Platform Tuninggoogle/skills | 21k | — | ~9.6k | Automated safety check: Pass | Apache-2.0 | |
| Agent Platform Tuning Managementgoogle/skills | 21k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
- Official
Agent Platform Tuning
google/skills
Agent Platform Model Tuning. An agent skill from google/skills.
- Official
Agent Platform Tuning Management
google/skills
Manages GenAI tuning jobs in Agent Platform. An agent skill from google/skills.
Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Od Tune Collab
nexu-io/open-design
Default reference pipeline for the tune-collab taskKind — pick a direction, patch-edit the existing artifact, critique, hand off.
More from egorfedorov/claude-context-optimizer
All 13 skills in this repoSmart Loader
egorfedorov/claude-context-optimizer
Automatically suggests optimal files to preload based on the user's task description and historical context patterns.
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
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)
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
Cco Shield
egorfedorov/claude-context-optimizer
Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste
Cco Task
egorfedorov/claude-context-optimizer
Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or…
Questions about Cco Config
What does Cco Config do?
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap. Cco Config is an agent skill from egorfedorov/claude-context-optimizer.
How do I install Cco Config in Claude Code?
Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a claude-code`. Or copy the skill folder (skills/cco-config in egorfedorov/claude-context-optimizer) into .claude/skills/cco-config in your project. Claude Code loads it when a task matches its description.
How do I install Cco Config in Codex?
Run `npx skills add egorfedorov/claude-context-optimizer --skill cco-config -a codex`. Or copy the skill folder (skills/cco-config in egorfedorov/claude-context-optimizer) into .agents/skills/cco-config in your project. Codex loads it when a task matches its description.
Can I use Cco Config 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-config -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-config, .gemini/skills/cco-config, .github/skills/cco-config and .opencode/skills/cco-config in your project.
What does Cco Config need to run?
Going by SKILL.md and its folder, Cco Config needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Bash(node ${CLAUDE_PLUGIN_ROOT}/src/config.js:*).
Does Cco Config 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 Config 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 Config use?
Cco Config 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 Config use?
About 839 tokens (SKILL.md is roughly 3.4k 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 Config?
Skills that share tags, products or a category with Cco Config: LLM Fine Tuning (sickn33/agentic-awesome-skills, 47k stars), Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars), Agent Platform Tuning (google/skills, 21k stars) and Agent Platform Tuning Management (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cco Config?
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.