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 skills add sixfeetup/intervals-mcp --skill intervals-time-entriesgit clone --depth 1 https://github.com/sixfeetup/intervals-mcpWrote 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/sixfeetup/intervals-mcp/intervals-time-entries)<a href="https://agentmods.dev/skills/sixfeetup/intervals-mcp/intervals-time-entries"><img src="https://agentmods.dev/badge/skills/sixfeetup/intervals-mcp/intervals-time-entries/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sixfeetup/intervals-mcp/intervals-time-entries"><img src="https://agentmods.dev/badge/skills/sixfeetup/intervals-mcp/intervals-time-entries.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.02359 |
| Opus 5 | $0.00015 | $0.01179 |
| Sonnet 5 | $0.00006 | $0.00472 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
intervals-time-entries 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 9d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intervals Time Entries
Overview
Time entry classification should be history-guided, not guess-driven. Never assume a timer should be started just because work is beginning. Before creating or changing timers/time entries, inspect recent local timers and time entries, ask for confirmation before starting any timer unless the user explicitly requested it, and use similar prior work to choose project/worktype/module.
When to Use
Use this skill for any request involving Intervals time tracking, including:
- starting a timer, e.g. “add timer for FOU-406” or “start a timer for Clubhouse”
- stopping or editing a timer
- adding retroactive time entries
- fixing failed syncs
- reviewing recent time entries or answering “what did I log?”
- choosing project, worktype, or module for time tracking
Required Context Check
Always gather context before creating, editing, or syncing a time entry or timer:
- Check recent time entries with
mcp__plugin_intervals_intervals__list_time. - Check active/recent timers with
mcp__plugin_intervals_intervals__list_timerswhen the request involves timers or could be affected by an active timer. Before starting a new timer, if any active timer exists, ask whether it should be stopped first. - Use
mcp__plugin_intervals_intervals__query_timefor date-scoped requests such as “today”, “yesterday”, “this week”, or when recent entries are not enough. - Use
mcp__plugin_intervals_intervals__find_project_contextto resolve project names, ticket prefixes, worktypes, modules, and ambiguous project matches. - Use the current working directory and path as an additional clue. For example, if the user is working under a client/project repo, prefer recent entries and project matches related to that repo.
Do not skip the recent-entry check just because the user supplied a ticket key or project name.
No Implicit Timer Starts
When work is beginning but the user did not explicitly ask to start a timer:
- Ask whether an Intervals timer should be started for this work.
- Do not start a timer until the user answers yes.
- Do not treat a coding task, project name, ticket key, current directory, or prior time-entry pattern as permission to start a timer.
- If the user says no or does not answer, continue the work without starting a timer.
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.
- 9d ago First seen · 163 lines · 29 tokens per session scan A de47865c7c36
intervals-time-entries is a skill published in the GitHub repository sixfeetup/intervals-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,359 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.