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 AraneaDev/claude-timestamp --skill time-awarenessgit clone --depth 1 https://github.com/AraneaDev/claude-timestampWrote 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/araneadev/claude-timestamp/time-awareness)<a href="https://agentmods.dev/skills/araneadev/claude-timestamp/time-awareness"><img src="https://agentmods.dev/badge/skills/araneadev/claude-timestamp/time-awareness/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.
<a href="https://agentmods.dev/skills/araneadev/claude-timestamp/time-awareness"><img src="https://agentmods.dev/badge/skills/araneadev/claude-timestamp/time-awareness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.00820 |
| Opus 5 | $0.00037 | $0.00410 |
| Sonnet 5 | $0.00015 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
time-awareness 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Time awareness
claude-timestamp tells you about time in short system reminders. They state facts and nothing else. This is what to do with them.
The reminders
Message sent at local time 10:37:21 CEST, after a 3h break arrives with
every prompt. It is when the user pressed enter, not the time now.
Turn running 30m04s (prompt sent 10:37:21); now 11:07:25 CEST. means the
turn you are in has run that long without hearing from the user.
- Check that the work still matches what was asked. Drift costs less to catch now than at the end.
- From the second one onward, consider finishing the step you are on and reporting back instead of opening new scope. That is a judgement call: a long job the user asked you to run unattended should keep going.
That Bash call took 2m14s. means one call was slow. Before running the
same thing again:
- run it with
run_in_backgroundand keep working meanwhile, - narrow it: one test file, one package, a filter, or
- reuse the output you already have, when nothing it depends on has changed.
Previous session in this project ended 14h ago (Thu 20:12:05). and
Resuming this conversation; last activity 14h ago (Thu 20:12:05). mean
that what you knew before the gap may be stale. Before building on it, check
what could have moved: the branch and git status, running servers, open
pull requests and CI runs, and files the user may have edited meanwhile.
Time in general
- During a long turn, get the current time from
date. The last stamp in the conversation is when the user spoke. - Refer to earlier messages by the time on their stamp ("the change you asked for at 10:37") rather than "earlier" or "just now".
- Write absolute dates in anything that outlives the conversation: "Thursday" becomes 2026-09-10.
- Answer questions about duration from measurement, never from how long the conversation feels.
Measuring
This session so far:
bash "${CLAUDE_SKILL_DIR}/../../hooks/scripts/setup.sh" --session
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.
- today First seen · 76 lines · 74 tokens per session scan A 47dee6401ef4
time-awareness is a skill published in the GitHub repository AraneaDev/claude-timestamp (3 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 820 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
mode-interactive
The interactive implementation posture (/foundry:mode-interactive) — the default lean direct loop. The operator drives edit→verify→merge in one accountable context; the operator reviews the diff at the merge button (the Regular-mode segregation). Sibling of mode-autonomous; they differ ONLY at the two ends (who paces…
familiar-help
Use familiar companion tools for creative buddy/companion interactions. Handles fortunes, code roasts, haiku, stats, mood, lore, focus timers, and personality changes. Triggers when user addresses their companion by any name — "buddy" (Anthropic's UI label), "familiar", "companion", or whatever name the user uses for…
spell-schedule
Schedule a moflo spell to run on the local machine via the moflo daemon (cron, interval, or one-time). Use when the user wants to schedule, automate, or recurringly run one of THEIR spells locally — e.g. "schedule the oap spell every hour", "run my audit spell every weekday at 9am", "fire X once tomorrow morning".…
pacer
Report Claude Code usage from Pacer — every rate-limit window, including per-model caps like Fable and each account on the machine — and pace heavy work against them, so hitting a limit during a long autonomous run or a large fan-out of subagents costs a resumable pause rather than the whole run. Use before and during…
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.
git-workflow
Use when starting feature work that needs a branch, creating worktrees for isolation, making atomic commits during development, or completing a development branch via merge, PR, preserve, or discard. Also use when the user says "set up worktree", "create PR", "finish this branch", "start feature", or when you need an…