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/primeline-ai/claude-code-starter-system/context-statsgit clone --depth 1 https://github.com/primeline-ai/claude-code-starter-systemWrote 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/primeline-ai/claude-code-starter-system/context-stats)<a href="https://agentmods.dev/commands/primeline-ai/claude-code-starter-system/context-stats"><img src="https://agentmods.dev/badge/commands/primeline-ai/claude-code-starter-system/context-stats.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 | $0.00583 |
| Opus 5 | $0.00005 | $0.00292 |
| Sonnet 5 | $0.00002 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
context-stats 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 4d ago.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/context-stats
Show how much of your context window is currently used, with a visual indicator and action recommendations.
Workflow
Step 1: Read Context Percentage
Run this bash command to find the latest context file:
ls -t /tmp/claude-context-pct-*.txt 2>/dev/null | head -1 | xargs cat 2>/dev/null
If the command returns nothing or fails, skip to the "Not Available" fallback at the bottom.
Store the result as {pct} (an integer 0-100).
Step 2: Generate Visual Bar
Calculate the filled and empty portions for a 30-character wide bar:
filled = round(pct * 30 / 100)
empty = 30 - filled
bar = "█" * filled + "░" * empty
Step 3: Determine Status
| Range | Status | Label |
|---|---|---|
| 0-59% | Healthy | Healthy |
| 60-79% | Warning | Warning |
| 80-100% | Critical | Critical |
Step 4: Render the Dashboard
╔═══════════════════════════════════════════════════════╗
║ CONTEXT WINDOW USAGE ║
╠═══════════════════════════════════════════════════════╣
║ {bar} {pct}% ║
║ ║
║ Status: {status label} ║
╠═══════════════════════════════════════════════════════╣
║ {recommendations} ║
╚═══════════════════════════════════════════════════════╝
Step 5: Recommendations by Status
Healthy (0-59%):
CAPACITY
Good capacity for complex tasks
Multi-step operations safe
Warning (60-79%):
RECOMMENDATIONS
Consider running /handoff soon
Avoid starting new complex tasks
Current work can continue safely
Critical (80-100%):
ACTION REQUIRED
Run /handoff now to save your session
Start a new session for fresh context
Use: continue - to resume where you left off
Not Available Fallback
If no context file was found, output:
Context percentage not available. Check your statusline configuration.
To enable context tracking, add the statusline script to your shell config.
See the plugin README for setup instructions.
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.
- 4d ago First seen · 102 lines · 9 tokens per session scan A d58f79bfcbd8
context-stats is a command published in the GitHub repository primeline-ai/claude-code-starter-system (5 stars, last pushed 19d ago), licensed MIT. It adds 9 tokens to every session and 583 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 2026-08-31.
Other commands, from other repositories
go-review
Go code review for idiomatic patterns.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
test
Run all PandaFilter verification steps in order. Stop and report on first failure. This is the required pre-commit gate.