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/everyone-needs-a-copilot/claude-copilot/configgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/config)<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/config"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/config.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 5.1 | $0.00000 | $0.02303 |
| Opus 5 | $0.00000 | $0.01151 |
| Sonnet 5 | $0.00000 | $0.00461 |
| Haiku 4.5 | $0.00000 | $0.00230 |
Grade A, and why
config 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.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration Dashboard
Display and manage Claude Copilot configuration settings, including ecomode thresholds, cost tracking preferences, and other framework settings.
Step 1: Detect Intent
Parse user input to determine action:
| Pattern | Action |
|---|---|
/config (no args) |
Show current configuration |
/config ecomode enable |
Enable ecomode |
/config ecomode disable |
Disable ecomode |
/config ecomode thresholds |
Show/update thresholds |
/config ecomode cost |
Show cost tracking settings |
/config reset |
Reset to defaults |
Step 2: Load Current Configuration
Configuration is stored in Memory Copilot metadata. Use these tools:
-
Get ecomode configuration from memory:
cc memory list --tags ecomode_config -
If no config exists, use defaults:
- enabled: false (ecomode off by default)
- thresholds.low: 0.3 (haiku below 0.3)
- thresholds.medium: 0.7 (sonnet below 0.7)
- cost.displayInMemory: true (show in /memory)
- cost.trackUsage: true (track model usage)
Step 3: Display Configuration
Show Current Configuration
Format as clean dashboard:
## Claude Copilot Configuration
### Ecomode
**Status:** [Enabled / Disabled]
**Model Routing Thresholds:**
- Low complexity (haiku): < 0.3 (default: 0.3)
- Medium complexity (sonnet): < 0.7 (default: 0.7)
- High complexity (opus): >= 0.7
**Cost Tracking:**
- Display in /memory: [Yes / No]
- Track usage: [Yes / No]
**How it works:**
- Tasks are scored 0.0-1.0 based on complexity (keywords, file count, agent type)
- Scores below 0.3 → haiku (fast, low cost)
- Scores 0.3-0.7 → sonnet (balanced)
- Scores 0.7+ → opus (complex work)
- Override anytime with keywords: `eco:`, `fast:`, `max:`, `opus:`, `sonnet:`, `haiku:`
**Current Session Cost Summary:**
Per-session cost summary is not currently available — no cost-tracking backend is wired into the framework. Cost figures shown in examples below are illustrative only.
### Configuration File
Configuration is stored in Memory Copilot at:
- Location: ~/.claude/memory/[workspace-id]/memory.db
- Tags: ecomode_config
- Type: context
To modify settings, use `/config ecomode [command]`
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 · 339 lines · 0 tokens per session scan A e43f7a610854
config is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,303 tokens. 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 2026-09-04.
Other commands, from other repositories
context
You are the Context Manager, responsible for monitoring and optimizing context usage during long implementation sessions. You help prevent context overflow and maintain efficiency.
version
Show version information and check for updates.
vulyk-status
Hive dashboard - open stories, memory freshness, skill stats, budget posture.
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.