Tooluck logoTooluck
SKILL.md

daily-budget-check

Agent skill fromhoangsonww/Claude-Code-Agent-Monitor

Run a daily spend check-in against a daily budget on the Agent Monitor dashboard — today's spend vs the daily target, pace through the day, and the projected overage if the current pace holds. Uses /api/pricing/cost and /api/sessions (grouped by started_at = today). Use for a quick daily spend check-in or a morning/evening budget pulse.

How to install daily-budget-check

install daily-budget-check
# install the Claude-Code-Agent-Monitor pack with the skills CLI
npx skills add hoangsonww/Claude-Code-Agent-Monitor

# or add only this skill to Claude Code: copy the folder

plugins/ccam-cost-guard/skills/daily-budget-check/

# into

~/.claude/skills/daily-budget-check/ (all projects)

.claude/skills/daily-budget-check/ (one project)

plugins/ccam-cost-guard/skills/daily-budget-check/SKILL.md

MITFull file
1# Daily Budget Check
2
3A fast daily pulse: are you on pace against today's budget?
4
5## Input
6
7The user provides: **$ARGUMENTS**
8
9This is the **daily budget in dollars** — e.g. `"5"` or `"$5/day"`. If omitted, ask
10for one or derive it from a monthly budget (`monthly / days_in_month`) and state the
11assumption.
12
13## Data Sources
14
15| Endpoint | Returns |
16|----------|---------|
17| `GET /api/pricing/cost` | `{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` — fleet-wide spend and the avg cost-per-session used to value today's sessions |
18| `GET /api/sessions?limit=200` | Session list with inline `cost` and `started_at` — filter to today (`DATE(started_at) = today`) to isolate today's spend |
19
20## Method
21
22Spend has no per-day field, so isolate **today** from the session list:
23
241. **Today's sessions** = sessions whose `started_at` is today (local date).
252. **Today's spend** = sum of inline `cost` over today's sessions. If inline `cost` is absent for some rows, fall back to `today_session_count × (total_cost / total_session_count)` and flag it as approximate.
263. **Pace**: `fraction_of_day_elapsed = hours_since_midnight / 24`. `expected_by_now = daily_budget × fraction_of_day_elapsed`.
274. **Pace delta** = `today_spend − expected_by_now` (▲ ahead of budget / ▼ behind).
28…

Excerpt shown under the repository's MIT license.

More skills in Claude-Code-Agent-Monitor

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates