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/marcusgoll/spec-flow/budgetgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWhat 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 | $0.00025 | $0.03295 |
| Opus 5 | $0.00013 | $0.01648 |
| Sonnet 5 | $0.00005 | $0.00659 |
| Haiku 4.5 | $0.00003 | $0.00330 |
Grade A, and why
budget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
24h timestamp (GNU): !date --version 2>/dev/null | grep -q GNU && date -d '24 hours ago' -Iseconds || echo "N/A"
24h timestamp (BSD): !date --version 2>/dev/null | grep -q GNU || date -u -v-24H -Iseconds 2>/dev/null || echo "N/A"
Marketing deployments (24h): !SINCE=$(date --version 2>/dev/null | grep -q GNU && date -d '24 hours ago' -Iseconds || date -u -v-24H -Iseconds); gh run list --workflow=deploy-staging.yml --created="$SINCE" --json conclusion --jq 'length' 2>/dev/null || echo "0"
App deployments (24h): !SINCE=$(date --version 2>/dev/null | grep -q GNU && date -d '24 hours ago' -Iseconds || date -u -v-24H -Iseconds); gh run list --workflow=deploy-app-staging.yml --created="$SINCE" --json conclusion --jq 'length' 2>/dev/null || echo "0"
Railway CLI installed: !command -v railway >/dev/null 2>&1 && echo "✅ Yes" || echo "❌ No"
Railway usage: !railway usage 2>/dev/null || echo "Railway CLI not available"
Oldest deployment timestamp: !SINCE=$(date --version 2>/dev/null | grep -q GNU && date -d '24 hours ago' -Iseconds || date -u -v-24H -Iseconds); gh run list --workflow=deploy-staging.yml --created="$SINCE" --limit 1 --json createdAt --jq '.[0].createdAt' 2>/dev/null || echo ""
Recent deployment statuses: !SINCE=$(date --version 2>/dev/null | grep -q GNU && date -d '24 hours ago' -Iseconds || date -u -v-24H -Iseconds); gh run list --workflow=deploy-staging.yml --created="$SINCE" --limit 10 --json conclusion,createdAt,displayTitle --jq '.[] | "\(.conclusion) - \(.displayTitle) - \(.createdAt)"' 2>/dev/null || echo ""
What it does:
- Counts Vercel deployments in 24h rolling window (Marketing + App)
- Checks Railway compute usage (if CLI available)
- Calculates quota reset time from oldest deployment
- Predicts remaining quota after next deployment
- Provides deployment strategy based on quota status
- Analyzes recent deployment failure rate
Operating constraints:
- Vercel Limit — 100 deployments per 24 hours (rolling window)
- Warning Threshold — Alert when < 20 remaining
- Critical Threshold — Block when < 10 remaining
- Read-Only — Never modifies quotas or settings
- Non-Blocking — Always returns, even on errors
Dependencies:
- GitHub CLI installed and authenticated (gh auth login)
- Railway CLI optional (for compute usage tracking)
- Access to deploy-staging.yml and deploy-app-staging.yml workflows
-
Calculate total Vercel deployments:
- Sum Marketing + App deployments from context
- Calculate remaining: 100 - total_used
- Determine status:
- normal: >= 20 remaining (✅)
- warning: 10-19 remaining (⚠️)
- critical: < 10 remaining (🚨)
-
Display Vercel quota section:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Deployment Budget (24h rolling) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Vercel Deployments: Marketing (staging): {count} App (staging): {count} Total used: {total} / 100 Remaining: {remaining} {status_emoji} {STATUS} - {remaining} deployments {available/remaining/left} -
Display Railway usage (if CLI available):
- If Railway CLI installed, show usage output
- If not installed, show installation instructions:
⚠️ Railway CLI not installed Install: npm install -g @railway/cli
-
Calculate quota reset time:
- Extract oldest deployment timestamp from context
- Calculate reset time (24 hours from oldest)
- Calculate time remaining until reset (hours and minutes)
- Display:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Quota Reset Information ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Oldest deployment: {timestamp} Quota resets at: {reset_time} Time to reset: {hours}h {minutes}m
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.
- 3d ago First seen · 372 lines · 25 tokens per session scan A b44821e332e2
budget is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 3,295 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 2026-08-30.
Other commands, from other repositories
deploy-dev
Deploy latest Docker image to {{DEVMACHINE}} dev environment.
deployment
Basic production deployment setup for FastAPI applications.
remote-status
Check if remote Docker environment needs updating.
remote-deploy
Deploy latest Docker image to remote staging environment.
fleet
Manage OpenClaw installations across multiple servers - assess state, push updates, notify users.
d1-migration
Run D1 migration workflow — generate, inspect, apply.