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 virgil-king/kbtz --skill kbtz-basicsgit clone --depth 1 https://github.com/virgil-king/kbtzWrote 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/virgil-king/kbtz/kbtz-basics)<a href="https://agentmods.dev/skills/virgil-king/kbtz/kbtz-basics"><img src="https://agentmods.dev/badge/skills/virgil-king/kbtz/kbtz-basics/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/virgil-king/kbtz/kbtz-basics"><img src="https://agentmods.dev/badge/skills/virgil-king/kbtz/kbtz-basics.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 | $0.00063 | $0.02078 |
| Opus 5 | $0.00032 | $0.01039 |
| Sonnet 5 | $0.00013 | $0.00416 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
kbtz-basics 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 11d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kbtz Task Tracker Reference
Commands
| Command | Description |
|---|---|
kbtz add <name> <desc> [-p parent] [-c assignee] [-n note] [--agent type] [--paused] |
Create a task |
kbtz claim <name> <assignee> |
Claim a task |
kbtz claim-next <assignee> [--prefer text] |
Atomically claim the best available task |
kbtz steal <name> <assignee> |
Atomically transfer task ownership (requires user approval) |
kbtz release <name> <assignee> |
Release a claimed task |
kbtz done <name> |
Mark task complete (requires user approval first) |
kbtz reopen <name> |
Reopen a completed task |
kbtz pause <name> |
Pause a task (remove from active work and default listing) |
kbtz unpause <name> |
Unpause a paused task (return to open) |
kbtz describe <name> <desc> |
Update a task's description |
kbtz reparent <name> [-p parent] |
Change a task's parent (omit -p to make root-level) |
kbtz rm <name> [--recursive] |
Remove a task (--recursive to remove children) |
kbtz list [--status S] [--json] [--tree] [--all] [--root name] [--children name] |
List tasks |
kbtz show <name> [--json] |
Show task details and blockers |
kbtz note <name> [content] |
Add a note to a task (reads stdin if content omitted) |
kbtz notes <name> [--json] |
List notes for a task |
kbtz block <blocker> <blocked> |
Set dependency (blocker must finish before blocked can start) |
kbtz unblock <blocker> <blocked> |
Remove a blocking relationship |
kbtz agents |
List configured agent types |
kbtz watch [--root name] |
Launch interactive TUI |
kbtz wait |
Block until database changes |
Task Naming
Task names must be kebab-case: lowercase letters, numbers, and hyphens only. Names are immutable — they cannot be changed after creation, so choose carefully.
Session ID
Use $KBTZ_SESSION_ID as your assignee in all kbtz commands. This environment variable is set automatically by Claude Code.
kbtz claim my-task $KBTZ_SESSION_ID
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.
- 11d ago First seen · 206 lines · 63 tokens per session scan A 1b02cfaabdec
kbtz-basics is a skill published in the GitHub repository virgil-king/kbtz (2 stars, last pushed 26d ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,078 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
Codex
Mission control: create tasks, assign to an agent/team, wait for human approval, worker runs in the background, accept results.
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.
dos-goal-fleet
Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.
dos-next-up
Snapshot the repo's phased-plan portfolio into a dispatch packet: audit candidates with dos verify, render who-does-what, and emit a dos gate verdict. Use when you need the current next-work view before dispatching agents.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
squads-cli
Squads CLI — operate your AI workforce through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.