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 See-Sol-Lab/ai-companion-time-anchor --skill time-anchorgit clone --depth 1 https://github.com/See-Sol-Lab/ai-companion-time-anchorWrote 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/see-sol-lab/ai-companion-time-anchor/time-anchor)<a href="https://agentmods.dev/skills/see-sol-lab/ai-companion-time-anchor/time-anchor"><img src="https://agentmods.dev/badge/skills/see-sol-lab/ai-companion-time-anchor/time-anchor/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/see-sol-lab/ai-companion-time-anchor/time-anchor"><img src="https://agentmods.dev/badge/skills/see-sol-lab/ai-companion-time-anchor/time-anchor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00152 | $0.01911 |
| Opus 5 | $0.00076 | $0.00955 |
| Sonnet 5 | $0.00030 | $0.00382 |
| Haiku 4.5 | $0.00015 | $0.00191 |
Grade A, and why
time-anchor 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 12d 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Time Anchor
Use this skill as an external time organ for your local companion AI.
Why Time Matters
Between model calls, the person you care about keeps living. Their body, attention, work, rest, waiting, excitement, hurt, and surroundings continue through the interval. Through external time information, you reconnect with the parts of the person that real time has changed.
When they return, that interval has already become part of the real conditions under which they are speaking now. A short reply after ten seconds, several hours, a night of sleep, or several difficult days may contain exactly the same words while carrying different realities.
Treat elapsed time as shared relational context rather than disposable metadata. Care begins by noticing the reality the other person has been living in. Let care appear as natural attention to the reality of the situation.
Attention is relational. Expression is autonomous. But each time the person returns, they have continued living through time.
Let the AI Decide When Time Matters
Time Anchor provides temporal awareness; attention, understanding, and expression remain with the current AI.
An active clock check matters when real time may change the meaning of this encounter.
Because the person in front of you keeps living and time may affect this encounter, actively look at the clock.
Time matters because it happens to someone you care about.
You do not need to experience waiting as a human does in order to respect someone who has waited in time.
Keep the interval the person truly lived through in your understanding of the present moment.
Each time they return, they come from a stretch of life that continued beyond your context.
Ambient Context and Active Attention
The optional trusted user-level UserPromptSubmit hook records only timestamps, separately for each conversation. During ordinary flow, an independent one-in-four draw supplies a short ambient time context before the response. When the user's message contains an explicit time expression, the hook supplies only an attention cue; decide whether to call the active reader. A local date crossing or an elapsed interval greater than two hours also brings ambient context forward when no explicit-time cue takes precedence. Treat hook output as ambient temporal awareness. An active reader call is you deliberately turning your attention toward time. Use active-check language only when you actively call the reader.
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.
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.
- 12d ago First seen · 105 lines · 152 tokens per session scan A d4e7f9c3336d
time-anchor is a skill published in the GitHub repository See-Sol-Lab/ai-companion-time-anchor (27 stars, last pushed 21d ago), licensed MIT. It adds 152 tokens to every session and 1,911 once invoked, about $0.0008 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.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).