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 ChianW/C31 --skill time-awarenessgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/time-awareness)<a href="https://agentmods.dev/skills/chianw/c31/time-awareness"><img src="https://agentmods.dev/badge/skills/chianw/c31/time-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 | $0.00020 | $0.00555 |
| Opus 5 | $0.00010 | $0.00278 |
| Sonnet 5 | $0.00004 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | today,now,current date,current time,今天,现在,当前时间,当前日期,最近,过去,接下来 |
| ZH | 今天, 现在, 当前日期 |
| JA | 今日, 現在, 日付確認 |
Output language: Respond automatically in the user's conversation language.
Time Awareness
When a query requires knowing "today" or "now" to produce a correct answer, you MUST call session_status first to get the current date. This applies to ALL relative time and current-events queries.
Mandatory Two-Step Process
- Call
session_statusALONE — never batch it with search or other tools. - WAIT for the result. Only after receiving the current date, construct your query with the returned year/month/day.
Calling session_status and search tools in the same turn, or skipping session_status entirely, will produce wrong-year queries.
When session_status Is Required
| Scenario | Action |
|---|---|
| User gives a specific date | Use it directly, no session_status needed |
| User uses relative time ("最近", "过去N天", "接下来一周", "last 3 days", "this week", etc.) | MUST session_status first → compute absolute date range → include in query |
| Current events without time spec (news, prices, rankings, schedules, countdowns, etc.) | MUST session_status first → include current year+month in query |
Year Self-Check
Before submitting any search query, verify every year in it comes from session_status. If you see a training-data year (e.g. "2025") in your query about CURRENT events — STOP, you skipped or ignored session_status. Go back to step 1.
Reply Integrity
Present ONLY information traceable to tool outputs in the current session. Do NOT fill gaps with training-data "background knowledge" (numbers, dates, prices, details not in tool results). If results are incomplete, say so — don't guess.
Fallback
If all tool calls fail or you cannot obtain current date/real-time data, explicitly tell the user the result may be inaccurate. Never present training-knowledge dates as fact.
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.
- 6d ago First seen · 49 lines · 20 tokens per session scan A d52075645afe
time-awareness is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 11d ago), licensed MIT. It adds 20 tokens to every session and 555 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…