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.
npx agentmods add commands/kevinzai/commander/ccc-context-budgetgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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.
[](https://agentmods.dev/commands/kevinzai/commander/ccc-context-budget)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-context-budget"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-context-budget.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.00352 |
| Opus 5 | $0.00012 | $0.00176 |
| Sonnet 5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
ccc-context-budget 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 yesterday.
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.
What it actually says
Context Budget Analyzer
Analyze your Claude Code context window consumption and produce a visual report with actionable recommendations.
Usage
/context-budget # Summary with gauge and top recommendations
/context-budget --verbose # Full breakdown per component
$ARGUMENTS
What to Do
Run the context-budget skill (skills/context-budget/SKILL.md) with the following inputs:
- Pass
--verboseflag if present in$ARGUMENTS - Assume a 200K context window (Claude Sonnet default) unless the user specifies otherwise
- Follow the skill's five phases: Inventory → Classify → Visual Report → Recommendations → Quick Actions
- Show the visual gauge, zone indicator, and session-save nudge if usage is high
- Always end with the Quick Actions block
Zone Thresholds
| Usage | Zone | Action |
|---|---|---|
| 0-50% | GREEN | Continue normally |
| 50-70% | YELLOW | Monitor, consider compacting soon |
| 70-80% | ORANGE | /ccc-save-session now, then compact or start fresh |
| 80-90% | RED | /ccc-save-session immediately |
| 90%+ | DANGER | STOP. Save and start new session. |
Related Commands
/ccc-save-session— Save current state for resumption/ccc-resume-session— Load saved state in fresh context/compact— Built-in Claude Code command to compress conversation history
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.
- yesterday First seen · 43 lines · 23 tokens per session scan A 297b6173216b
ccc-context-budget is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 352 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 2026-09-03.
Other commands, from other repositories
remember
Explicitly save something to memory as an experience.
evolution
Show what the system learned and changed recently.
rust-teach
One-time setup that scans your Rust project, understands its patterns and conventions, and writes a Rust-specific context section to your CLAUDE.md. Run once per project to establish persistent Rust guidelines.
trace
Use trace to save repo context, implementation notes, and package/file/branch memory.
codex-state
List saved Codex task state for the current workspace so a controller can resume the right thread.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.