kco-agentsmd
Analyze AGENTS.md files for token bloat and suggest optimizations
Skill by egorfedorov
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/egorfedorov-kco-agentsmd
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/kco-agentsmd
What's inside
- Skill name
kco-agentsmd- Description
- Analyze AGENTS.md files for token bloat and suggest optimizations
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# AGENTS.md Analyzer
Analyze AGENTS.md files in the current project for token bloat and optimization opportunities.
Run the analyzer:
```bash
node ${KIMI_SKILL_DIR}/../../src/agentsmd-analyzer.js "${CWD}"
```
Present the output to the user. The analyzer checks for:
- **Overall size** — files over 2K tokens get flagged
- **Large sections** — sections over 1K tokens
- **Duplicate lines** — repeated content
- **Verbose patterns** — "please make sure to", "it is important that", etc.
- **Long code blocks** — examples over 20 lines
- **Excessive whitespace** — empty lines eating tokens
For each issue found, explain the savings potential and suggest a concrete fix.
If the user wants to apply fixes, help them edit the AGENTS.md directly using the Edit tool.From egorfedorov/kimi-context-optimizer, MIT.
More from egorfedorov/kimi-context-optimizer
- 0.529score
kco-budget
egorfedorov
Configure token budget limits, auto-compact settings, optional token pricing, and view current budget status (window-aware — reads the active model's context…
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-task
egorfedorov
Organize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done.
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-pack
egorfedorov
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
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco
egorfedorov
Context Control Center — one screen for budget, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-overhead
egorfedorov
Audit the fixed context overhead every session starts with — system prompt, plugins, skills, AGENTS.md — measured from the real wire transcript
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-coach
egorfedorov
Analyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better…
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-doctor
egorfedorov
Health check for the kimi-context-optimizer plugin install — verifies versions, hooks, data dir, config, and reports any issues
SkillCFreshness: C★ 6Claude Code +9 - 0.526score
kco-shield
egorfedorov
Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste
SkillCFreshness: C★ 6Claude Code +9 - 0.526score
kco-smart-loader
egorfedorov
Automatically suggests optimal files to preload based on the user's task description and historical context patterns
SkillCFreshness: C★ 6Claude Code +9 - 0.526score
kco-roi
egorfedorov
Calculate monthly token savings and ROI from using the context optimizer
SkillCFreshness: C★ 6Claude Code +9 - 0.523score
kco-replay
egorfedorov
Show recent session summaries for quick context recovery
SkillCFreshness: C★ 6Claude Code +9 - 0.523score
kco-digest
egorfedorov
Show weekly/daily efficiency digest with score and trends
SkillCFreshness: C★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 18, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from egorfedorov
- 0.529score
kco-doctor
egorfedorov
Health check for the kimi-context-optimizer plugin install — verifies versions, hooks, data dir, config, and reports any issues
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-pack
egorfedorov
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
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco
egorfedorov
Context Control Center — one screen for budget, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-coach
egorfedorov
Analyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better…
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-budget
egorfedorov
Configure token budget limits, auto-compact settings, optional token pricing, and view current budget status (window-aware — reads the active model's context…
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
kco-task
egorfedorov
Organize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done.
SkillCFreshness: C★ 6Claude Code +9
Cite this page
kco-agentsmd skill. Agent Mart. https://agentmart.dev/skills/egorfedorov-kco-agentsmd (last updated 2026-10-24)