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 skills/sent1nelx/claude-activity-tracker/activitynpx skills add Sent1nelX/claude-activity-tracker --skill activitygit clone --depth 1 https://github.com/Sent1nelX/claude-activity-trackerWrote 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/skills/sent1nelx/claude-activity-tracker/activity)<a href="https://agentmods.dev/skills/sent1nelx/claude-activity-tracker/activity"><img src="https://agentmods.dev/badge/skills/sent1nelx/claude-activity-tracker/activity.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 | $0.00020 | $0.01108 |
| Opus 5 | $0.00010 | $0.00554 |
| Sonnet 5 | $0.00004 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
activity 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Tracker Skill
Use this skill when the user types /activity or asks about their Claude Code usage, coding stats, session summaries, or productivity metrics.
Instructions
Step 1 — Fetch today's stats
Call the activity_stats MCP tool (server: activity-tracker):
tool: activity_stats
arguments: {}
This returns a JSON object with:
date— today's datesession_count— number of sessions startedtotal_duration_minutes— total active timetool_calls— total MCP/tool invocationsfiles_edited— number of unique files touchedtop_files— list of{path, edits}objects (up to 10)top_tools— list of{tool, calls}objects (up to 10)
Step 2 — Format the output
Present results as a clean markdown summary. Use the template below, substituting real values:
## 📊 Today's Activity — {date}
| Metric | Value |
|--------|-------|
| Sessions | {session_count} |
| Active time | {total_duration_minutes} min |
| Tool calls | {tool_calls} |
| Files edited | {files_edited} |
### 🔧 Top Tools
| Tool | Calls |
|------|-------|
| {tool} | {calls} |
... (repeat for each entry)
### 📁 Top Files
| File | Edits |
|------|-------|
| {path} | {edits} |
... (repeat for each entry)
Shorten file paths to the last 2-3 path segments for readability (e.g. src/server.py instead of /home/user/projects/foo/src/server.py).
Step 3 — Offer weekly view (optional)
After showing today's stats, offer: "Type /activity week for a 7-day report."
If the user asked for weekly stats (e.g. said "weekly", "this week", "7 days"), call activity_report instead:
tool: activity_report
arguments: { "days": 7 }
Format the weekly report similarly, but add a daily breakdown table:
### 📅 Daily Breakdown
| Date | Sessions | Duration | Tools |
|------|----------|----------|-------|
| {date} | {sessions} | {minutes} min | {tools} |
Step 4 — Insight (optional, 1 sentence)
If any single tool accounts for more than 40% of calls, note it: "You relied heavily on {tool} today — it accounted for {pct}% of all tool calls."
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 · 164 lines · 20 tokens per session scan A 1f42be498e48
activity is a skill published in the GitHub repository Sent1nelX/claude-activity-tracker (2 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,108 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 2026-08-31.
Other skills, from other repositories
cost-audit
Analyzes the current session's token usage, pinpoints where tokens were wasted, and produces concrete optimization actions.
auth-middleware
Generates authentication and authorization middleware for Express/Fastify/Hono.
caching-strategy
Adds caching to expensive operations - Redis, in-memory, HTTP cache headers.
cron-job
Creates a cron job with error handling, logging, locking, and monitoring.
graphql-schema
Generates or reviews a GraphQL schema with types, queries, mutations, and resolvers.
mobile-perf
Audits React Native app for performance issues - FlatList, re-renders, bridge calls.