intervals-time-entries

intervals-time-entries is a skill for Claude Code from sixfeetup/intervals-mcp. It costs 29 tokens per session (2,359 once invoked), scanned A, original, MIT.

A set of instructions for managing Intervals timers and time entries, which record how much time was spent on specific work.

In plain words
What is it for?
Use it to start, stop, edit, review, sync, or add past Intervals time entries.
Why use it?
It helps avoid guessing the right project or work category and checks existing entries before changing tracking data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the intervals plugin — 8 skills, 1 MCP server shipped together

Good fit Use it to start, stop, edit, review, sync, or add past Intervals time entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sixfeetup/intervals-mcp/intervals-time-entries
Install

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.

Any agent
npx skills add sixfeetup/intervals-mcp --skill intervals-time-entries
Clone the repo
git clone --depth 1 https://github.com/sixfeetup/intervals-mcp

Made for: Claude Code.

Or install intervals, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

Wrote 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.

agentmods badge for intervals-time-entries

README.md
[![agentmods](https://agentmods.dev/badge/skills/sixfeetup/intervals-mcp/intervals-time-entries/github.svg)](https://agentmods.dev/skills/sixfeetup/intervals-mcp/intervals-time-entries)
Your own site
<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.

agentmods 80×15 button for intervals-time-entries

Your own site · 80×15
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash de47865c7c36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/intervals-time-entries/SKILL.md · 163 lines

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:

  1. Check recent time entries with mcp__plugin_intervals_intervals__list_time.
  2. Check active/recent timers with mcp__plugin_intervals_intervals__list_timers when 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.
  3. Use mcp__plugin_intervals_intervals__query_time for date-scoped requests such as “today”, “yesterday”, “this week”, or when recent entries are not enough.
  4. Use mcp__plugin_intervals_intervals__find_project_context to resolve project names, ticket prefixes, worktypes, modules, and ambiguous project matches.
  5. 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:

  1. Ask whether an Intervals timer should be started for this work.
  2. Do not start a timer until the user answers yes.
  3. Do not treat a coding task, project name, ticket key, current directory, or prior time-entry pattern as permission to start a timer.
  4. If the user says no or does not answer, continue the work without starting a timer.

Read the full file on GitHub · 163 lines

Changes

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.

  1. 9d ago First seen · 163 lines · 29 tokens per session scan A de47865c7c36

Subscribe to this mod's changes

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.