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 pablo-albaladejo/kaiord --skill kaiord-workout-filesgit clone --depth 1 https://github.com/pablo-albaladejo/kaiordWrote 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/pablo-albaladejo/kaiord/kaiord-workout-files)<a href="https://agentmods.dev/skills/pablo-albaladejo/kaiord/kaiord-workout-files"><img src="https://agentmods.dev/badge/skills/pablo-albaladejo/kaiord/kaiord-workout-files/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/pablo-albaladejo/kaiord/kaiord-workout-files"><img src="https://agentmods.dev/badge/skills/pablo-albaladejo/kaiord/kaiord-workout-files.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 | $0.00042 | $0.00717 |
| Opus 5.5 | $0.00017 | $0.00287 |
| Sonnet 5.5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
kaiord-workout-files 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaiord workout files
Kaiord converts structured workout files between FIT, TCX, ZWO (Zwift),
GCN (Garmin Connect JSON) and KRD, its canonical JSON format. Every
conversion goes through KRD. Where both formats can express a step, values
survive within fixed tolerances (time ±1 s, power ±1 W or ±1 %FTP, heart
rate ±1 bpm, cadence ±1 rpm). Where the target cannot express one (for
example a Garmin repetition-count end condition, which becomes an open
duration in KRD), Kaiord logs a Lossy conversion: warning naming what it
substituted.
Use this skill when a user wants to move a workout between training platforms, check that a file survives a conversion, or read what a workout file contains.
Option A: the MCP server (preferred for agents)
Add the stdio server to the client configuration:
{
"kaiord": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@kaiord/mcp"]
}
}
Tools:
kaiord_list_formatslists the supported formats and what each can do.kaiord_convertconverts between FIT, TCX, ZWO, GCN and KRD.kaiord_inspectparses any supported file and summarizes it.kaiord_validatevalidates KRD JSON against the schema.kaiord_diffcompares two workout files.kaiord_extract_workoutextracts the structured workout definition.kaiord_round_trip_validatechecks a FIT file only: FIT → KRD → FIT, reporting drift beyond the tolerances. It does not accept TCX or ZWO and does not compare a converted file with its source.
Resources: kaiord://schema/krd (KRD JSON Schema), kaiord://formats,
kaiord://docs/krd-format.
Option B: the CLI
npm install -g @kaiord/cli
kaiord convert --input workout.fit --output workout.krd
kaiord convert --input "workouts/*.fit" --output-dir converted/
kaiord validate --input workout.fit
The format is detected from the file extension; override it with
--input-format.
Rules
- Convert through KRD; do not hand-edit FIT binaries.
- Before telling the user a converted file is safe to upload, check the
actual output:
kaiord_inspectit andkaiord_diffit against the source.kaiord_round_trip_validatecovers FIT sources only. - Report every
Lossy conversion:warning to the user; never present a lossy conversion as exact. - Kaiord runs locally. Do not upload a user's workout files anywhere to convert them.
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 · 79 lines · 42 tokens per session scan A 75c4f683c5a3
kaiord-workout-files is a skill published in the GitHub repository pablo-albaladejo/kaiord (11 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 717 once invoked, about $0.0002 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 2026-10-29.
kaiord-workout-files compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kaiord-workout-filespablo-albaladejo/kaiord | Skill | 11 | 4d ago | MIT | A | 42 | Claude Code, Codex |
| enrich-exceltinyfish-io/tinyfish-cookbook | Skill | 2.3k | 3d ago | MIT | A | 92 | Claude Code, Codex |
| pandic-officeTeam-Commonly/commonly | Skill | 1.4k | yesterday | Apache-2.0 | A | 59 | Claude Code, Codex |
| pdfTeam-Commonly/commonly | Skill | 1.4k | yesterday | Apache-2.0 | A | 49 | Claude Code, Codex |
| ui5wc-upgradeUI5/webcomponents-react | Skill | 542 | yesterday | Apache-2.0 | A | 79 | Claude Code |
| ima-knowledge-basecountbot-ai/CountBot | Skill | 784 | 7d ago | MIT | A | 67 | Claude Code, Codex |
| azure-ai-document-intelligence-tsbenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 45 | Claude Code, Codex |