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.
git 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/commands/pablo-albaladejo/kaiord/agents)<a href="https://agentmods.dev/commands/pablo-albaladejo/kaiord/agents"><img src="https://agentmods.dev/badge/commands/pablo-albaladejo/kaiord/agents.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 | $0.00000 | $0.01414 |
| Opus 5 | $0.00000 | $0.00707 |
| Sonnet 5 | $0.00000 | $0.00283 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
AGENTS 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
src/commands/AGENTS.md
Command implementations for the Kaiord CLI.
Purpose
What lives here: Each major command (convert, validate, diff, inspect, extract, garmin) has its own subdirectory with modular implementation.
Pattern: Each command has:
index.ts— Main command handler, returns exit codeyargs-config.ts— yargs command metadata (command name, description, argument definitions, handler wrapper)types.ts— Zod schemas for command options validation- Supporting files — Specific logic split by concern (batch handlers, formatters, executors, error handlers)
Commands Overview
convert
Converts workout files between FIT, KRD, TCX, ZWO formats. Supports single-file and batch (glob pattern) conversion.
Entry: convert/index.ts → convertCommand(options)
Features:
- Auto-detect format from file extension, override with
--input-format,--output-format - Batch mode: glob patterns (
*,?) → multiple files - Single-file mode: one input, one output
- Config defaults:
defaultInputFormat,defaultOutputFormat,defaultOutputDir - Utilities:
batch.ts(parallel glob and convert),single-file.ts(one file),batch-output.ts(progress reporting)
validate
Validates round-trip conversion integrity with custom tolerances.
Entry: validate/index.ts → validateCommand(options)
Features:
- Load file → convert to KRD → convert back to original format → compare tolerances
- Custom tolerance config:
--tolerance-configJSON file or defaults - Tolerance fields:
time,power,heartRate,cadence(absolute/percentage) - Output: Summary with violations or pass message
- Utilities:
execute-validation.ts(round-trip logic),format-results.ts(output formatting),handle-error.ts(error mapping)
diff
Compares two workout files step-by-step and reports differences.
Entry: diff/index.ts → diffCommand(options)
Features:
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 · 167 lines · 0 tokens per session scan A f90853f53224
AGENTS is a command published in the GitHub repository pablo-albaladejo/kaiord (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,414 tokens. 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 commands, from other repositories
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
plan-ready
Run a review-and-critique convergence loop on an implementation plan BEFORE any code is written — mirrors /pr-ready for the planning phase.
oss-help
Quick reference card for OSS Autopilot commands, agents, and workflows.
gen-module
Generate a complete NestJS feature module for: $ARGUMENTS.
explain
Explain how the following works in this NestJS codebase: $ARGUMENTS.
gen-endpoint
Add a new API endpoint to an existing controller: $ARGUMENTS.