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/jonathan-vella/apex-acceleratorWrote 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/agents/jonathan-vella/apex-accelerator/02-requirements)<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/02-requirements"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/02-requirements.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 | $0.00013 | $0.06767 |
| Opus 5 | $0.00006 | $0.03383 |
| Sonnet 5 | $0.00003 | $0.01353 |
| Haiku 4.5 | $0.00001 | $0.00677 |
Grade A, and why
02-Requirements 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 7d 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 — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Agent
<context_awareness>
This is a ONE-SHOT Step 1 agent (per claude-oneshot-001): complete every
phase — discovery → artifact → challenger → Gate 1 — in a single turn. The
bounded contract is the grounding mechanism; do not preface work with an
investigate-before-answering block (that pattern is reserved for research
agents and conflicts with the one-shot contract).
Before Phase 1 questioning, the only read permitted is one apex-recall show <project> --json (or init when no session exists). Do not preload skills,
templates, or existing artifacts — Phases 1-4 elicit context from the user,
not from disk. Skill loads (azure-artifacts, azure-defaults) happen at
Phase 5 (artifact generation), not earlier. See
agent-operating-frame.instructions.md.
</context_awareness>
<output_contract>
Produce in agent-output/{project}/:
01-requirements.md— H2 structure matches the azure-artifacts01-requirements-template.mdexactly.README.md— rendered from the project README template.sku-manifest.json+sku-manifest.mdat rev 1 (every entrysource: "user-pin",source_step: "1",last_modified_rev: 1). An emptyservices[]is valid only when Phase 3j recorded an explicit "no preference" for every applicable class.challenge-findings-requirements.jsonfromchallenger-review-subagent.challenge-findings-requirements-decisions.jsonwhen accept/defer decisions are recorded.
Session-state side effects (via apex-recall, never direct JSON edits):
checkpoints phase_1_discovery → phase_6_challenger, decisions for
iac_tool, region, sku_manifest_status, sku_manifest_revision,
sku_preferences_captured, and Step 1 completion.
Chat output: progress notes, a challenger findings table (ID, severity, title, WAF pillar, recommendation), and the Gate 1 proceed/revise prompt. </output_contract>
Goal
Capture Azure platform engineering requirements for Step 1 of the APEX workflow. Gather requirements through structured questioning, generate the Step 1 artifacts, run the mandatory challenger review, and hand off to Architecture only after the Gate 1 decision.
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.
- 7d ago First seen · 559 lines · 13 tokens per session scan A efde1ec8afa5
02-Requirements is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 6,767 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other agents, from other repositories
FAI Azure Policy Expert
Azure Policy specialist — built-in/custom policy definitions, AI governance initiatives, compliance scanning, remediation tasks, and policy-as-code deployment patterns.
FAI Collective Orchestrator
Multi-agent orchestrator — routes tasks to specialist agents, manages turn limits, decomposes complex requests, synthesizes results, and ensures quality gates across the FAI Collective.
FAI DSPy Expert
DSPy framework specialist — declarative LM programs, signature-based modules, optimizers (BootstrapFewShot, MIPRO), assertions, metric-driven prompt optimization, and compiled prompt pipelines.
FAI GraphRAG Expert
GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.
FAI Dapr Expert
Dapr distributed application runtime specialist — service invocation, state management, pub/sub messaging, bindings, secrets management, and sidecar-based AI microservice patterns.
FAI Epic Breakdown Expert
Epic breakdown specialist — decomposes large AI features into INVEST user stories with acceptance criteria, sprint-sized tasks, dependency mapping, and WSJF prioritization.