A time-formatting helper that changes UTC times into the user's local timezone before showing them. UTC is a worldwide reference time, while CEST and CET are Central European local times.

It helps format user-facing timestamps while keeping internal logs, database values, and time calculations in UTC.

It prevents users from having to convert displayed times themselves and avoids confusing times in messages, charts, dashboards, and summaries.

format-time — Skill for Claude Code by leopu00

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/leopu00/job-hunter-team

agentmods

npx agentmods add skills/leopu00/job-hunter-team/format-time

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/format-time/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/format-time)

Your own site

<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/format-time"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/format-time/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/format-time"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/format-time.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 764 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00054	$0.00764
Opus 5	$0.00027	$0.00382
Sonnet 5	$0.00011	$0.00153
Haiku 4.5	$0.00005	$0.00076

Measured 9d ago against content hash 4d9ef18cf674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

format-time 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 9d 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.

agents/_skills/format-time/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

format-time — UTC → user timezone in user-facing output

Bug #15: the container runs in UTC, the user lives in CEST/CET. Without conversion every "reset at 03:11" in chat or charts forces the user to do +2 in their head — and sometimes the user says "qui sono le 3:21" and the Capitano has to scramble for the conversion.

When to use

Apply it whenever you produce a timestamp the user will read:

Telegram messages from any agent (Capitano, Assistente, Mentor)
Matplotlib chart subtitles, x-tick labels, legends
Dashboard widgets that show time
Log lines or summaries returned to the user

Skip when:

Writing internal log files (messages.jsonl, sentinel-data.jsonl, dottore-actions.jsonl) — they stay UTC ISO for cross-agent parsing.
Writing DB columns — keep UTC ISO so the dashboard can format on render.
Computing intervals / deltas — work in UTC, format only at the edges.

How to use

from shared.skills.format_time import fmt_user, fmt_user_with_utc
from datetime import datetime, timezone

now = datetime.now(timezone.utc)
print(fmt_user(now))            # "03:21 CEST"
print(fmt_user_with_utc(now))   # "03:21 CEST (01:21 UTC)"

Or, from bash:

python3 /app/shared/skills/format_time.py --now
python3 /app/shared/skills/format_time.py --iso 2026-05-17T01:14:00Z --with-utc

When to show both user-time and UTC

In operational charts that an oncall engineer (or you, debugging) might read alongside the team's UTC logs, prefer fmt_user_with_utc so both are visible:

"Now 03:21 CEST (01:21 UTC) — usage 63% — proj 92.2%"

In plain Telegram chat to the user, fmt_user alone is usually enough:

"📅 Reset finestra 5h alle 05:11 CEST (~1h 50m)."

Where the user timezone comes from

candidate_profile.yml::timezone (IANA name, e.g. Europe/Rome). Default Europe/Rome if missing — covers ~95% of beta users. To override per session: JHT_USER_TZ env var (read by the helper).

Anti-patterns

Read the full file on GitHub · 81 lines

Files

What ships with it

6 files 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.

Changes

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.

9d ago First seen · 81 lines · 54 tokens per session scan A 4d9ef18cf674

Subscribe to this mod's changes

format-time is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 764 once invoked, about $0.0003 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.

Localization ai ai-agents artificial-intelligence automation career cli

vs-item-onboarding

Match the language of the user's most recent message in every line of prose you write — confirmation prompts, status notes, hand-off summaries, questions, error explanations, and any internal thinking / reasoning / planning output that the host may surface (e.g. blocks, "thinking" panels, scratchpad notes, todo…

volcengine/SearchCLI · 86 tokens

i18n-check

Finds the three ways translations silently rot: a key added to the default locale but never copied to the others (missing), a key copied but never translated (still reads identical to the source), and a key left behind in one locale after being renamed or removed from the default (orphan). Also catches new UI copy…

mgiovani/cc-arsenal · 225 tokens

bazarr

This skill should be used when the user wants to manage subtitles in Bazarr. Triggers include: "missing subtitles", "wanted subtitles", "search subtitles", "download subtitles", "subtitle providers", "Bazarr status", "is Bazarr running", "what subtitles are missing", "find subtitles for", or any mention of subtitle…

dinglebear-ai/yarr · 0 tokens

format-time