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 log_detectivegit 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/log_detective)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/log_detective"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/log_detective/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/log_detective"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/log_detective.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 | $0.00044 | $0.10469 |
| Opus 5.5 | $0.00018 | $0.04188 |
| Sonnet 5.5 | $0.00009 | $0.02094 |
| Haiku 4.5 | $0.00004 | $0.01047 |
Grade A, and why
log-detective 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Detective — turn a wall of log lines into the three things you needed.
summarise level counts, time span, busiest minute, top error signatures
signatures cluster near-identical errors by shape, not text
timeline events per bucket, so a spike has a timestamp
grep filtered lines with surrounding context
No network, no credentials, no parsing config. Handles plain text, and reads JSON-lines logs structurally when it detects them.
WHY IT CLUSTERS BY SIGNATURE INSTEAD OF COUNTING LINES
Ten thousand errors are usually four errors. Raw counts hide that: every line differs by a request id, a timestamp, a port number, so nothing groups and you scroll. Normalising the variable parts — numbers, hex ids, UUIDs, paths, quoted strings — collapses them into a handful of shapes, and the shape is the bug.
WHY 'BUSIEST MINUTE' IS ITS OWN NUMBER
An incident is a spike, and a spike is invisible in a total. Knowing that 80% of the day's errors landed inside one minute changes what you go and look at.
WHY IT NEVER PHONES HOME
Logs are the single most PII-dense artifact most systems produce. Anything that uploads them to be "analysed" is a data-egress decision disguised as a feature. This reads local files and returns local results.
Parameters
The typed contract this capability answers to (JSON Schema — the deterministic layer):
{
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"summarise",
"signatures",
"timeline",
"grep"
],
"description": "What to do."
},
"path": {
"type": "string",
"description": "Path to the log file."
},
"pattern": {
"type": "string",
"description": "For grep: a regular expression."
},
"context": {
"type": "integer",
"description": "For grep: lines of context. Default 1."
},
"top": {
"type": "integer",
"description": "How many signatures/buckets. Default 10."
}
},
"required": [
"action",
"path"
]
}
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 · 213 lines · 44 tokens per session scan A 163d659d4873
log-detective is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 10,469 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.
log-detective compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| log-detectivemicrosoft/aibast-agents-library | Skill | 8 | yesterday | MIT | A | 44 | 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 |