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/florianbruniaux/claude-code-plugins/costsgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/costs)<a href="https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/costs"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/costs.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 | $0.00009 | $0.00523 |
| Opus 5 | $0.00005 | $0.00262 |
| Sonnet 5 | $0.00002 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
costs 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 today.
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
Costs Analysis Command
Launch ccboard and jump directly to the costs tracking and analytics tab.
Features
-
3 Views:
- Overview: Total costs and breakdown
- By Model: Cost per AI model (Opus, Sonnet, Haiku)
- Daily Trend: Cost evolution over time
-
Token Breakdown:
- Input tokens (prompt)
- Output tokens (generation)
- Cache read tokens (reused)
- Cache write tokens (stored)
-
Pricing: Automatic calculation based on 2024 Anthropic rates
Usage
# Open costs tab directly
/costs
# Alternative: run with tab argument
ccboard --tab costs
Costs Tab Navigation
1: Overview view2: By Model view3: Daily Trend viewTab: Switch between views↑/↓: Scroll through data
Example Output
Total Tokens: 17.32M
Total Cost: $9,145.20
Breakdown by Model:
- Opus 4.5: 76% ($7,828) ████████████████
- Sonnet 4.5: 14% ($1,314) ███
- Haiku 3.5: 10% ($3) █
Token Distribution:
- Input: 10.70M (65%)
- Output: 4.58M (28%)
- Cache Read: 1.01M (6%)
- Cache Write: 1.04B (1%)
Requirements
ccboard must be installed. Run /ccboard-install if needed.
Implementation
#!/bin/bash
# Check if ccboard is installed
if ! command -v ccboard &> /dev/null; then
echo "❌ ccboard is not installed"
echo "Run: /ccboard-install"
exit 1
fi
# Launch ccboard with Costs tab (tab index 5, accessible with '6' key)
# For now, launch and user presses '6'
exec ccboard
Note: Currently launches ccboard in dashboard view. Press 6 to access Costs tab.
Future version will support ccboard --tab costs for direct access.
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.
- today First seen · 85 lines · 9 tokens per session scan A abed6307210b
costs is a command published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 523 once invoked, about $0.0000 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 2026-09-04.
Other commands, from other repositories
aso
App Store Optimization command. iOS app listing analysis via the iTunes API, keyword optimization, and competitor comparison.
content-generate
Social media content generation command. Produces ready-to-use posts, captions, visual briefs, and hashtags for the given platform and type.
api-doc
API documentation generation. Scans route definitions and produces structured API docs.
audit
Quality audit command. Runs a systematic audit over code, structure, or process.
brief
Project briefing command. Turns raw project ideas into structured, actionable briefs.
changelog
Automatic changelog generation. Produces a structured changelog from commit history.