Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add dodobrands/ai-hub/plugin install timeWrote 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/dodobrands/ai-hub/time-chat)<a href="https://agentmods.dev/skills/dodobrands/ai-hub/time-chat"><img src="https://agentmods.dev/badge/skills/dodobrands/ai-hub/time-chat/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/dodobrands/ai-hub/time-chat"><img src="https://agentmods.dev/badge/skills/dodobrands/ai-hub/time-chat.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 | $0.00096 | $0.00932 |
| Opus 5.5 | $0.00038 | $0.00373 |
| Sonnet 5.5 | $0.00019 | $0.00186 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
time-chat 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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Time (Mattermost) read skill
When a Time permalink or a "read DMs with @user" request appears, fetch the content via the plugin's bash wrappers and summarise it for the user.
Trigger
Activate on any of:
- A permalink URL:
https://<host>/<team>/pl/<post_id>(query/fragment ok) - A request to read DMs / личные сообщения with a specific
@user - A search request against Time/Mattermost ("найди в тайме …")
Read
First resolve the helper once — independent of the current directory. This skill is
activated from an arbitrary CWD (a marketplace plugin lives in a cache dir; a team overlay
may vendor this repo as a git subtree and symlink the skill into ~/.claude/skills/), so a
bare integrations/time/scripts/... path does not resolve. The snippet below finds
time-messages.sh for every install model, with no consumer-specific knowledge:
_t=""
# 1) marketplace (Claude Code / Copilot / Cursor): $CLAUDE_PLUGIN_ROOT → this plugin's dir
[ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && [ -f "$CLAUDE_PLUGIN_ROOT/scripts/time-messages.sh" ] && _t="$CLAUDE_PLUGIN_ROOT"
# 2) subtree + skill symlink (a team overlay vendoring ai-hub): find our own symlink, walk up
if [ -z "$_t" ]; then for _d in "$HOME"/.claude/skills/*; do
[ -L "$_d" ] || continue; _r="$(readlink -f "$_d" 2>/dev/null)"
case "$_r" in */integrations/time/skills/time-chat)
[ -f "${_r%/skills/time-chat}/scripts/time-messages.sh" ] && { _t="${_r%/skills/time-chat}"; break; } ;;
esac
done; fi
# 3) Copilot _direct install
[ -z "$_t" ] && [ -f "$HOME/.copilot/installed-plugins/_direct/time/scripts/time-messages.sh" ] && _t="$(readlink -f "$HOME/.copilot/installed-plugins/_direct/time")"
# 4) plain git clone (run from anywhere inside it)
[ -z "$_t" ] && _r="$(git rev-parse --show-toplevel 2>/dev/null)" && [ -f "$_r/integrations/time/scripts/time-messages.sh" ] && _t="$_r/integrations/time"
TIME_MESSAGES="$_t/scripts/time-messages.sh"
The scripts accept permalinks directly — no manual id extraction.
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.
- 2mo ago First seen · 81 lines · 96 tokens per session scan A ca9d28f84ac4
time-chat is a skill published in the GitHub repository dodobrands/ai-hub (9 stars, last pushed 13d ago), licensed MIT. It adds 96 tokens to every session and 932 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-04.
time-chat compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| time-chatdodobrands/ai-hub | Skill | 9 | 13d ago | MIT | A | 96 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 113k | today | MIT | A | 30 | Claude Code, Codex |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 4d ago | MIT | A | 184 | Claude Code |
| feishuHmbown/CodeWhale | Skill | 41k | 2d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 13d ago | MIT | A | 52 | Claude Code, Codex |