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 toolwright-adk/toolwright-monorepo --skill temporal-awarenessgit clone --depth 1 https://github.com/toolwright-adk/toolwright-monorepoWrote 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/toolwright-adk/toolwright-monorepo/temporal-awareness)<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>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 | $0.00071 | $0.01043 |
| Opus 5 | $0.00036 | $0.00522 |
| Sonnet 5 | $0.00014 | $0.00209 |
| Haiku 4.5 | $0.00007 | $0.00104 |
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. 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):
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.
- 7d ago First seen · 118 lines · 71 tokens per session scan C 9e7b8134a42c
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.
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.
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.…
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…
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.
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…
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.