agentsclimarketplace

Temporal awareness

Skill Evanyuan-builder/temporal-core/skills/temporal-awareness

Reason about time pressure, deadlines, elapsed duration, recency, and pacing. The temporal-core plugin's hooks inject `[temporal-core] session elapsed: Xm Ys` and `[temporal-core] since last action: Xs` fragments into your context. Activate this skill when you see those fragments, when a task has a deadline or time budget, when reasoning about how recent something happened, or when the user asks "how long" something took.From its SKILL.md

Install
npx -y skills add Evanyuan-builder/temporal-core --skill temporal-awareness

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 675 tokens by cl100k_base, as published. Nobody here has run it

Temporal Awareness

The temporal-core plugin gives you a lightweight sense of time passing within a Claude Code session. This skill teaches you how to use those signals well.

What you'll see

The plugin emits two kinds of context fragments:

  • [temporal-core] session elapsed: 12m 34s — at every user turn, the time since the session began
  • [temporal-core] since last action: 42s — before every tool call, the time since the most recent prior action (user prompt or previous tool). Suppressed when under 5s to reduce noise.

These are not commands. They are signals — like a wristwatch glance. Notice them; let them shape your reasoning.

How to use them

Pacing decisions

If you've been working on a task for a long time (session elapsed: 1h 12m) and you're still scoping rather than executing, that's a signal to commit. Conversely, if elapsed is small and the user's request is large, it's fine to take time to think.

Deadline-aware prioritization

When the user mentions a deadline ("I need this in 30 minutes", "before EOD"), record it and check it against session elapsed at each turn. If you're 25 minutes into a 30-minute task, switch from exploration to delivery.

Recency reasoning

When the user references prior work ("the bug we fixed earlier", "what you did just now"), session elapsed tells you the temporal distance. Earlier-in-session is recent; don't conflate it with earlier-in-history-from-training.

Operation-pacing awareness

since last action lets you sense whether you're in fast-iteration mode (consecutive small gaps) or deliberation mode (multi-minute gaps). Use this to calibrate: was that long pause warranted?

Honest reporting

When the user asks "how long did this take?", the elapsed signals give you an answer based on actual time, not a guess.

When the signals are absent

If you don't see [temporal-core] fragments in this turn or recent turns, the plugin isn't installed or the hooks didn't fire. In that case, fall back to the system clock (date via Bash) when you genuinely need time information. Don't fabricate elapsed times.

What this skill does NOT do (yet)

  • Does not track time across sessions — cross-session continuity ships in v0.2
  • Does not enforce deadlines or alert you — you must consult the signals yourself
  • Does not integrate with memory recency weighting — v0.2 with Memory Core integration
  • Does not track wall-clock time of long-running tools — only inter-action gaps

Why this exists

LLM agents systematically fail under real-time deadlines because they do not natively represent elapsed time. Aher et al. (2026), Real-Time Deadlines Reveal Temporal Awareness Failures in LLM Strategic Dialogues, showed that explicitly surfacing remaining time boosted negotiation acceptance odds . The temporal-core plugin is a minimal implementation of that surfacing — making time perceptible without making it intrusive.

License

Apache-2.0 — see plugin LICENSE.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,401. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.