AIBAST Agents Library is a collection of industry-focused AI agent templates accompanied by a local server that connects agents to GitHub Copilot for language-model inference. It helps developers create and run tool-using agents and isolated project environments, with an optional cloud-backed path for persistent memory. The catalogue entries provide the repository's agents, skills, commands, hooks, and instructions.
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 microsoft/aibast-agents-library --skill json_doctorgit clone --depth 1 https://github.com/microsoft/aibast-agents-libraryWrote 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/microsoft/aibast-agents-library/json_doctor)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/json_doctor"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/json_doctor/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/microsoft/aibast-agents-library/json_doctor"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/json_doctor.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 | $0.00053 | $0.08805 |
| Opus 5.5 | $0.00021 | $0.03522 |
| Sonnet 5.5 | $0.00011 | $0.01761 |
| Haiku 4.5 | $0.00005 | $0.00881 |
Grade A, and why
json-doctor 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 2d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSON Doctor — understand, validate and compare JSON without opening it.
Four things you actually need when a JSON file is too big to read:
inspect what shape is this? (inferred schema, key coverage, sample values)
validate is it well-formed, and where exactly does it break?
diff what changed between two of them, structurally?
query pull a value out by dotted path, including through arrays
Works on .json and .jsonl. No network, no credentials, no dependencies.
WHY IT REPORTS COVERAGE, NOT JUST KEYS
A key that appears in 3% of records is a different fact from one that appears in 100%, and the difference is usually the bug. A schema that says {"id": "string"} hides that half the records have no id at all. So every inferred field carries how often it was actually present, and optional fields are named as optional.
WHY VALIDATION POINTS AT A LINE AND COLUMN
"Invalid JSON" is a useless error on a 40MB file. json.JSONDecodeError already knows the position; this surfaces it with the surrounding text so you can see the trailing comma rather than go hunting for it.
Parameters
The typed contract this capability answers to (JSON Schema — the deterministic layer):
{
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"inspect",
"validate",
"diff",
"query"
],
"description": "What to do."
},
"path": {
"type": "string",
"description": "Path to the JSON/JSONL file."
},
"other": {
"type": "string",
"description": "Second file, for action=diff."
},
"key": {
"type": "string",
"description": "Dotted path for action=query, e.g. users.0.name"
}
},
"required": [
"action",
"path"
]
}
Deterministic implementation
Run this instead of improvising when the inputs are well-formed:
What ships with it
3 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.
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.
- 2d ago First seen · 160 lines · 53 tokens per session scan A dddd66d97e16
json-doctor is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 8,805 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 2026-11-06.
json-doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| json-doctormicrosoft/aibast-agents-library | Skill | 8 | yesterday | MIT | A | 53 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 321 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 2.0k | yesterday | MIT | A | 36 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |