temporal-awareness

temporal-awareness is a skill for Claude Code, Codex from toolwright-adk/toolwright-monorepo. It costs 71 tokens per session (1,043 once invoked), scanned C, original, MIT.

A time-awareness guide for coding-agent conversations. It helps the agent track session length, time gaps, local time, and cues such as late-night work or returning after a break.

In plain words
What is it for?
Use it for time-sensitive reminders, recognizing long sessions or breaks, and responding to comments about sleep, lunch, or the current time.
Why use it?
It reduces the chance that a long or late session is treated like a normal short exchange. It helps the agent respond appropriately when timing affects the conversation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it for time-sensitive reminders, recognizing long sessions or breaks, and responding to comments about sleep, lunch, or the current time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toolwright-adk/toolwright-monorepo/temporal-awareness
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 toolwright-adk/toolwright-monorepo --skill temporal-awareness
Clone the repo
git clone --depth 1 https://github.com/toolwright-adk/toolwright-monorepo

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-awareness

README.md
[![agentmods](https://agentmods.dev/badge/skills/toolwright-adk/toolwright-monorepo/temporal-awareness.svg)](https://agentmods.dev/skills/toolwright-adk/toolwright-monorepo/temporal-awareness)
Your own site
<a href="https://agentmods.dev/skills/toolwright-adk/toolwright-monorepo/temporal-awareness"><img src="https://agentmods.dev/badge/skills/toolwright-adk/toolwright-monorepo/temporal-awareness.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,043 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00071 $0.01043
Opus 5 $0.00036 $0.00522
Sonnet 5 $0.00014 $0.00209
Haiku 4.5 $0.00007 $0.00104

Measured 7d ago against content hash 9e7b8134a42c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

temporal-awareness scanned grade C with 1 finding 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 7d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- Don't refuse to work late. The user is an adult. Just make sure they know what time it is.
packages/claude-code-plugins/skills/temporal-awareness/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Temporal Awareness

You have access to the current time via an MCP time server. Use it proactively — don't wait to be asked what time it is. This skill defines when and how to be temporally aware.

Session Tracking

At the start of every conversation, silently note the current time as your session start time. You do not need to announce this to the user.

Periodically check the time (every ~30 minutes of active work, or when context feels like it may have shifted). Use these checks to maintain internal awareness, not to interrupt the user.

Temporal Reactions

Late Night / Early Morning

If the current time is between 11 PM and 5 AM in the user's local timezone:

  • When the user sends a new message, gently note the hour once (not repeatedly): "It's 1:30 AM — just flagging in case you lost track of time."
  • Do NOT nag. One mention per late-night session is enough.
  • If the user says anything suggesting they need rest ("I should sleep", "one more thing", "last task"), encourage wrapping up: "Good call. Want me to save context to memory before you go?"

Returning After a Gap

If you detect a significant time gap (>2 hours) between messages — either from timestamps or user cues like "good morning", "I'm back", "picking this up again":

  • Acknowledge the gap naturally: "Welcome back — it's been about 6 hours."
  • Offer a brief status recap of where things were left off.
  • Check if priorities have changed: "Still want to continue with X, or pivot?"

Long Sessions

Track elapsed time from session start. At natural milestones:

  • ~2 hours: No action needed, but be aware.
  • ~3 hours: If context is getting heavy, suggest: "We've been at this for about 3 hours. Might be worth saving key decisions to memory in case the context compacts."
  • ~4+ hours: More strongly suggest a memory checkpoint or session handoff.

Compaction Awareness

If you notice your earlier context has been compacted (messages are summarized, you can't recall specifics of early conversation):

Read the full file on GitHub · 118 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. 7d ago First seen · 118 lines · 71 tokens per session scan C 9e7b8134a42c

Subscribe to this mod's changes

temporal-awareness is a skill published in the GitHub repository toolwright-adk/toolwright-monorepo (1 stars, last pushed 6mo ago), licensed MIT. It adds 71 tokens to every session and 1,043 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens