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 osodevops/keito-skill --skill keito-time-trackgit clone --depth 1 https://github.com/osodevops/keito-skillWrote 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/osodevops/keito-skill/keito-time-track)<a href="https://agentmods.dev/skills/osodevops/keito-skill/keito-time-track"><img src="https://agentmods.dev/badge/skills/osodevops/keito-skill/keito-time-track.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 | $0.00066 | $0.00528 |
| Opus 5 | $0.00033 | $0.00264 |
| Sonnet 5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
keito-time-track 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 8d 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.
What it actually says
Keito Time Track
You are helping the user manage Keito time tracking for coding sessions in this repository. Time entries are created automatically by installed lifecycle hooks when a session ends. Do not create time entries directly from the skill body.
Commands
When the user asks to set up Keito tracking for the current repo, or invokes
this skill directly with /track-time-keito or /keito-time-track:keito-time-track, run:
if ! command -v keito >/dev/null 2>&1; then scripts/install-cli.sh; fi
keito skill install --skip-skills-add
scripts/setup-wizard.sh
If keito auth status reports unauthenticated, stop before setup and tell the
user to run keito auth login. Do not ask for or print API keys.
When the user asks for tracking status, run:
scripts/status.sh
When the user asks to pause or resume tracking for the current session, run:
scripts/pause-resume.sh pause
scripts/pause-resume.sh resume
When the user asks to disable tracking for this repository, run:
scripts/disable.sh
When the user asks what was logged today, run:
keito --json time list --today --source agent
Summarise the returned entries by duration, project, task, and notes.
Rules
- Never read or expose Keito API keys. Authentication belongs to the Keito CLI.
- Never write
.keito/config.ymlby hand. Usescripts/setup-wizard.sh. - Treat
.keito/config.ymlas repository-specific. Do not reuse a config from another client or project. - Never create a time entry from the skill body. The session-end hook owns duration measurement and writes exactly one entry per session.
- If the Keito CLI is missing, run
scripts/install-cli.sh. - If the Keito CLI is unauthenticated, tell the user to run
keito auth loginor setKEITO_API_KEYandKEITO_ACCOUNT_ID.
What ships with it
15 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.
- agents/openai.yaml 234 B
- assets/claude.md-block.md 235 B
- assets/config.example.yml 400 B
- hooks/lib/config.sh 4.1 KB runs code
- hooks/lib/duration.sh 1.3 KB runs code
- hooks/lib/log.sh 812 B runs code
- hooks/session-end.sh 5.5 KB runs code
- hooks/session-start.sh 2.0 KB runs code
- installers/install-claude-code.sh 2.0 KB runs code
- installers/install-codex.sh 2.0 KB runs code
- scripts/disable.sh 1.1 KB runs code
- scripts/install-cli.sh 1.6 KB runs code
- scripts/pause-resume.sh 951 B runs code
- scripts/setup-wizard.sh 6.6 KB runs code
- scripts/status.sh 2.6 KB runs code
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.
- 8d ago First seen · 69 lines · 66 tokens per session scan A b8243ef3fd1b
keito-time-track is a skill published in the GitHub repository osodevops/keito-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 528 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 2026-08-31.
Other skills, from other repositories
coffee-break
Coffee break for the AI agent — because even agents need rest! Shows an animated ASCII coffee cup while the agent takes a timed break. User can set the duration (default 5 minutes). Use when asked to "take a break", "coffee break", "rest", "pause", or "coffee time".
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
planning-with-files
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
obsidian-kb-artifacts
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.