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 KxSystems/kx-skills --skill kx-playbackgit clone --depth 1 https://github.com/KxSystems/kx-skillsWrote 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/kxsystems/kx-skills/kx-playback)<a href="https://agentmods.dev/skills/kxsystems/kx-skills/kx-playback"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kx-playback/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/kxsystems/kx-skills/kx-playback"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kx-playback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 139 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 164 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.01918 |
| Opus 5.5 | $0.00040 | $0.00767 |
| Sonnet 5.5 | $0.00020 | $0.00384 |
| Haiku 4.5 | $0.00010 | $0.00192 |
Grade A, and why
kx-playback 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KX PlayBack Component
Also read kx-dashboard-core for: envelope, screen/widget wrapper, data sources, ViewState, binding patterns, actions, notifications, and the pre-flight checklist.
⚠️ PlayBack-Specific Hazards
keyis"PlayBack"— not"BasicComponents". This is the only component with a dedicated top-level key outside BasicComponents.Selectedmust be a ViewState binding — it receives the current playback position and drives all components that react to playback. Omitting it means nothing updates during playback.SelectedColumnmust match a column in the data source — it is the column whose value is published toSelectedat each playback step. If left blank, nothing is published.TimeColumnis only relevant inMode: "Time"— inMode: "Event"it is unused. InMode: "Time",TimeColumnspecifies the timestamp column used to derive playback timing.Mode: "Event"steps through data rows sequentially —IntervalTimecontrols the delay in seconds between steps.Mode: "Time"uses the values inTimeColumnto derive real elapsed time between steps.Playing: 0is the stopped state — do not setPlayingto a non-zero value in the initial JSON; the component manages this field at runtime.- **Data source must be sorted by
SelectedColumnusing`col xasc** — PlayBack steps through rows in the order they arrive from the data source; unsorted data produces non-sequential playback. Always prepend`<column> xascto the query, e.g.`Date xasc select distinct Date from SPX.
PLAYBACK
key: "PlayBack" · definitionId: "47" · version: "4.7.7"
A time-series playback controller. Steps through a data source row by row (Event mode) or by time (Time mode), publishing the current position to a ViewState that other components subscribe to.
Basics
{
"Name": "",
"Data": { "_dashboardsType": "data", "value": "<timeSeriesDataSource>" },
"Selected": { "_dashboardsType": "viewstate", "value": "<currentPositionViewState>" },
"SelectedColumn": "<value-column>",
"TimeColumn": "<timestamp-column>",
"Mode": "Event",
"Speed": "1x",
"Playing": 0,
"MaxOverallTime": 60,
"IntervalTime": 1,
"speedControl": false,
"multiStateControl": false,
"ForcePause": false,
"DisplayWarning": false
}
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 · 180 lines · 99 tokens per session scan A 62e98c06d20f
kx-playback is a skill published in the GitHub repository KxSystems/kx-skills (22 stars, last pushed 22d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,918 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 2026-08-30.
kx-playback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kx-playbackKxSystems/kx-skills | Skill | 22 | 22d ago | Apache-2.0 | A | 99 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |