cost-tracker SKILL.md skillA

cost-tracker from suryast/free-ai-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add suryast/free-ai-agent-skills/cost-tracker@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
suryast/free-ai-agent-skills
Path
cost-tracker/SKILL.md
Versions recorded
2
Latest version
v1.0.0, committed Oct 10, 2026
First version recorded
Feb 28, 2026
Size
8,020 bytes
Repository stars
2
License
MIT

Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget. Use when estimating task cost, checking token usage, or setting a session budget.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 💰 Cost Tracker

> Uses the Agent Skills package format. Execution depends on the host tools and permissions; consult the frontmatter compatibility requirements where provided.

Track what your AI sessions actually cost. Estimate token usage, cumulative spend, and warn you before you hit budget thresholds — across OpenAI, Anthropic, Google, and other major providers.

---

## Triggers

Activate this skill when:
- User asks "how much has this session cost?"
- User asks "what's my token usage?"
- User sets a session budget ("keep this under $2")
- User wants a cost estimate before a large task
- Cumulative session spend needs tracking
- "track my costs", "budget check", "token count", "how much am I spending"

---

## Pricing Reference (update as models change)

Use these rates to estimate costs. All prices are per 1M tokens (input / output).

### Anthropic
| Model | Input | Output |
|-------|-------|--------|
| claude-opus-4 | $15.00 | $75.00 |
| claude-sonnet-4 | $3.00 | $15.00 |
| claude-haiku-4 | $0.80 | $4.00 |
| claude-opus-3 | $15.00 | $75.00 |
| claude-sonnet-3.5 | $3.00 | $15.00 |
| claude-haiku-3.5 | $0.80 | $4.00 |

### OpenAI
| Model | Input | Output |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add suryast/free-ai-agent-skills/cost-tracker@sha256:3f28d8ffb921259f

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lhh36paqpnwwmgig.svg)](https://markdownregistry.com/a/art_lhh36paqpnwwmgig)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Feb 28, 2026 and Oct 10, 2026, about one every 224 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-10 ef59299 8,020 BA view · diff
v1.0.02026-02-28 f9c909d 7,875 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8020 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

suryast/free-ai-agent-skills · 2 stars · license MIT · pushed 2026-10-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lhh36paqpnwwmgig
GET https://markdownregistry.com/api/v1/resolve?ref=suryast/free-ai-agent-skills/cost-tracker
GET https://markdownregistry.com/api/v1/blob/3f28d8ffb921259f09b530454992dc084955c19c48a85fba20271c17df0c4423

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from suryast/free-ai-agent-skills

approval-blocked-maintenance-loops SKILL.md skill
suryast/free-ai-agent-skills · approval-blocked-maintenance-loops/SKILL.md · Stops repetitive maintenance retries at consent boundaries and preserves resumable evidence. Use when scheduled agents…
git:20261010.461cc7c · audit A · 2 stars
cron-composer SKILL.md skill
suryast/free-ai-agent-skills · cron-composer/SKILL.md · Composable block system for OpenClaw cron job prompts. Assembles cron prompts from reusable markdown blocks so…
git:20261010.2c2162d · audit A · 2 stars
cron-doctor SKILL.md skill
suryast/free-ai-agent-skills · cron-doctor/SKILL.md · Diagnose and triage cron job failures. Checks job states, identifies error patterns, prioritizes by criticality…
v1.1.0 · audit A · 2 stars
daily-archivist SKILL.md skill
suryast/free-ai-agent-skills · daily-archivist/SKILL.md · Daily knowledge quality audit and inter-agent coordination. Fact-checks memory files, fills knowledge gaps, cleans up…
v1.0.0 · audit A · 2 stars
explain-codebase SKILL.md skill
suryast/free-ai-agent-skills · explain-codebase/SKILL.md · Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points…
v1.0.0 · audit A · 2 stars
git-guardian SKILL.md skill
suryast/free-ai-agent-skills · git-guardian/SKILL.md · Pre-commit safety checks for AI-assisted development. Detects secrets, large files, merge conflict markers, sensitive…
v1.0.0 · audit A · 2 stars
narrated-motion-explainers SKILL.md skill
suryast/free-ai-agent-skills · narrated-motion-explainers/SKILL.md · Produces short captioned motion explainers by streaming Pillow frames into FFmpeg and verifying the finished MP4. Use…
git:20261010.461cc7c · audit A · 2 stars
self-monitor SKILL.md skill
suryast/free-ai-agent-skills · self-monitor/SKILL.md · Proactive self-monitoring of infrastructure, services, and health. Tracks disk/memory/load, service health, cron job…
v1.1.0 · audit B · 2 stars
skill-security SKILL.md skill
suryast/free-ai-agent-skills · skill-security/SKILL.md · Security audit tool for AI agent skills. Scans for credential harvesting, code injection, network exfiltration…
git:20261010.ef59299 · audit A · 2 stars
static-site-release-verification SKILL.md skill
suryast/free-ai-agent-skills · static-site-release-verification/SKILL.md · Verifies source, build artifacts, deployed revision, and clean-URL asset parity. Use when releasing a static site…
git:20261010.461cc7c · audit A · 2 stars
weekly-meta-audit SKILL.md skill
suryast/free-ai-agent-skills · weekly-meta-audit/SKILL.md · Automated weekly self-audit of agent operations, cron health, memory gaps, and process failures. Use when performing…
git:20261010.ef59299 · audit A · 2 stars

Every file in suryast/free-ai-agent-skills

Other files named cost-tracker

cost-tracker SKILL.md skill
rohitg00/pro-workflow · skills/cost-tracker/SKILL.md · Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
git:20260718.7f7209d · audit A · 2,940 stars
cost-tracker SKILL.md skill
felvieira/claude-skills-fv · skills/30-cost-tracker/SKILL.md · Skill de rastreamento de custo por sessao. Monitora tokens consumidos, chamadas de API (fal.ai, Brave…
git:20260909.2bf525b · audit A · 25 stars

Browse by kind, by grade A, or by owner.