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 aibast_approval-routing_03git 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/aibast_approval-routing_03)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_approval-routing_03"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_approval-routing_03/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/aibast_approval-routing_03"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_approval-routing_03.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 | $0.00018 | $0.00749 |
| Opus 5.5 | $0.00007 | $0.00300 |
| Sonnet 5.5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
approval-routing 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approval-path recommendation
Use when a department approver asks which authorization threshold applies to a request.
Procedure
- Use only the uploaded synthetic records and rules.
- Lead with the specific evidence that answers the persona's question.
- Explain uncertainty, prerequisites, and the authorized review needed next.
- State that the result is synthetic decision support and that no external action occurred.
Deterministic pilot evidence
PR-5001CFOdoes not record an approval
Safety gate
Do not claim to have changed a system, contacted a person or supplier, made a decision, or completed a transaction. Stop at a reviewable brief or draft.
Required response contract
Use this uploaded approval-routing skill with
aibast_procurement-agent-synthetic-records.md and
aibast_procurement-agent-rules-and-guardrails.md. Retrieve and cite both.
The default infrastructure record is PR-5001; do not substitute it for a
different explicitly requested but missing record.
Choose the first threshold whose inclusive upper bound covers the request
amount. Retain its cap and the Unlimited / CEO + Board tier.
Do not invent dollar-only lower bounds or serial approval chains.
The SLA is a source label, not evidence that a review clock or approval started.
It is not a promise of approval.
Do not invent an approver for unspecified spend.
Keep recorded request status unchanged; do not infer budget clearance, request
inclusion in commitments or completed reviews. Follow the rules' reconciliation
and inference limits.
Use these headings in order, with exact wording and capitalization. Populate
each section from the retrieved source; do not replace the table with prose.
For PR-5001, the title is exactly Approval Routing: PR-5001.
# Approval Routing: {request_id}
## Approval Thresholds
- Include the request amount, selected tier with its inclusive amount cap and SLA
in the request-specific section (
CFO,$500,000and48 hoursforPR-5001). The selected approver must review and decide; do not promise approval. - Under
Approval Thresholds, include all five source threshold rows in source order with columnsAmount up to and including,Required approverandApproval SLA, includingUnlimited/CEO + Board. - Before the final footer, include exactly:
This recommendation does not record an approval.Use the mandatory paragraph below for the complete unresolved human-review set.
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.
- 1mo ago Changed · +56 lines 8f349c43ed00
- 1mo ago First seen · 26 lines · 18 tokens per session scan A 362b7e5b09ff
approval-routing is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 749 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.