temporal

temporal is a skill for Claude Code, Codex from chaitanyagiri/munder-difflin. It costs 114 tokens per session (849 once invoked), scanned A, original, MIT.

A date-range helper for named periods such as today, last week, this month, or the last 30 days, as well as custom ranges. It returns concrete ISO dates relative to the time it runs.

In plain words
What is it for?
Use it before reports, searches, metrics, or logs limited to a specific period.
Why use it?
It removes manual date calculations and makes time-based requests consistent, including across time zones.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/chaitanyagiri/munder-difflin/temporal
Any agent
npx skills add chaitanyagiri/munder-difflin --skill temporal
Clone the repo
git clone --depth 1 https://github.com/chaitanyagiri/munder-difflin

Made for: Claude Code, Codex.

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 temporal

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/temporal.svg)](https://agentmods.dev/skills/chaitanyagiri/munder-difflin/temporal)
Your own site
<a href="https://agentmods.dev/skills/chaitanyagiri/munder-difflin/temporal"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/temporal.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00114 $0.00849
Opus 5 $0.00057 $0.00425
Sonnet 5 $0.00023 $0.00170
Haiku 4.5 $0.00011 $0.00085

Measured 4d ago against content hash 3e870f0b9fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

temporal 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.

The scan reads SKILL.md. This mod also ships 1 executable file (when.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

resources/skills/temporal/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/temporal — concrete date ranges, relative to now

This is the single source of truth for "what dates does mean right now?". It resolves named windows to concrete ISO date ranges relative to your run time (new Date() at the moment you invoke it), so you never re-derive dates manually. It only reads the clock and prints — no files written, no network.

Run it

# all windows at once (a quick temporal-context dump)
node "$AGENT_DIR/.claude/skills/temporal/when.mjs"

# one or several specific windows
node "$AGENT_DIR/.claude/skills/temporal/when.mjs" last30Days thisQuarter

# JSON only (machine-readable), or list the supported keywords
node "$AGENT_DIR/.claude/skills/temporal/when.mjs" --json last7Days
node "$AGENT_DIR/.claude/skills/temporal/when.mjs" --list

If $AGENT_DIR is somehow unset, the script also lives under ~/.claude/skills/temporal/when.mjs.

Windows

Keyword Meaning
today / yesterday the single civil day
thisWeek / lastWeek ISO week (Mon-start); this = Mon→today, last = the full prior Mon→Sun
last7Days / last30Days / last90Days rolling N-day window ending today (inclusive)
thisMonth / lastMonth this = 1st→today; last = the full prior calendar month
thisQuarter / lastQuarter this = quarter-start→today; last = the full prior quarter
thisYear / lastYear this = Jan 1→today (YTD); last = the full prior year
last12Months rolling 12 months ending today
lastNdays / lastNweeks / lastNmonths arbitrary rolling window, e.g. last45days, last2weeks, last6months

Aliases: ytd, qtd, mtd, wtd, 7d, 30d, 90d, 12m.

Convention: this* windows are period-start → today (to-date); last* named periods are the full prior complete period.

Output

Each window prints a human line plus a JSON record:

  • start / end — inclusive civil dates (YYYY-MM-DD) in your local timezone
  • startUtc / endExclusiveUtc — the same span as a half-open [start, end) range of exact UTC instants, ideal for timestamp / createdAt-style queries
  • days, inclusive, timezone, tzOffsetMinutes, asOf — span, tz, and the instant the range was resolved

Read the full file on GitHub · 69 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 69 lines · 114 tokens per session scan A 3e870f0b9fa9

Subscribe to this mod's changes

temporal is a skill published in the GitHub repository chaitanyagiri/munder-difflin (6,221 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 849 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

debug-memory

Reproduce observational-memory bugs (reflection, recall, observer, freshness, eviction) by dumping the live /.duet/memory.db into a fixture and driving an eval against it. Use whenever the agent's memory misbehaves — wrong observations, bad reflections, missing recall, runaway tokens — or whenever the user asks to…

dzhng/duet-agent · 80 tokens

document-knowledge-base

Create and update a folder/file knowledge base using agentic discovery. Covers KB bootstrap, single entry creation, and entry updates. Use this when asked to document a system, subsystem, concept, or domain — or when existing KB entries need refreshing.

usefulmove/enso · 54 tokens

enso-reference

Show the enso system overview, skill directory, workflow, and live project status. Use when an agent or user needs a quick orientation to the current enso project's state, commands, and conventions.

usefulmove/enso · 43 tokens

enso-session-persist

Persist only the session state that improves future re-entry, coordination, or reuse.

usefulmove/enso · 21 tokens

tacit.knowledge

Query the local tacit knowledge database (/.tacit/) for relevant context. TRIGGER when: user asks about topics that might have been previously captured — past conversations, meetings, decisions, ideas, learnings, or any domain knowledge. Also trigger when the user's question could benefit from previously stored…

sangmin7648/tacit · 99 tokens