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 jonathan-vella/apex-accelerator --skill apex-azure-governance-discoverygit 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/skills/jonathan-vella/apex-accelerator/apex-azure-governance-discovery)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-governance-discovery"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-governance-discovery/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/jonathan-vella/apex-accelerator/apex-azure-governance-discovery"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-governance-discovery.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 | $0.00089 | $0.01853 |
| Opus 5.5 | $0.00036 | $0.00741 |
| Sonnet 5.5 | $0.00018 | $0.00371 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
apex-azure-governance-discovery scanned grade A with 1 finding 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 23d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.check_output` monkeypatching — no Azure account required for tests. How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Governance Discovery Skill
Replaces the legacy governance-discovery-subagent with a deterministic script.
The skill exposes scripts/discover.py — a single batched REST traversal that
emits the schema-compliant 04-governance-constraints.json envelope. The parent
agent (04g-Governance) invokes it via run_in_terminal, reads a compact
one-line JSON status from stdout, and proceeds to artifact writing without ever
pulling raw Azure REST responses into LLM context.
When to Use
- Step 3.5 governance discovery for a project
- Refreshing the governance snapshot after policy changes
- Regenerating inputs for Step 4 (IaC Plan) and Step 5 (IaC Code)
When NOT to Use
- Writing
04-governance-constraints.md— that stays in the parent agent - Cross-referencing architecture resources — parent-side LLM work
- Challenger review orchestration — parent-side LLM work
- Any workflow that is not 04g-Governance
Rules
- Stay deterministic — the discovery script is a single batched REST traversal; no LLM calls, no retries that hide errors, no inferred policy effects
- Use compact status for routing, then targeted envelope reads for decisions; recover all required evidence and diagnostics
- Schema compliance is mandatory — envelope MUST conform to
tools/schemas/governance-constraints.schema.json(schema_version: governance-constraints-v1) - Property paths are always strings — use
""for unresolvable paths, nevernull - Defender filtering is narrow — the collector retains enforcement-bearing assignments;
--include-defender-autoretains all - Exit codes are contract —
0= COMPLETE,1= PARTIAL,2= FAILED; argparse errors also return nonzero. COMPLETE is collection status, not planning approval - No artifact writing — the script emits JSON + a
.preview.md; the agent owns the final04-governance-constraints.mdcontent and traffic-light rendering - Reuse only current scoped evidence — project, subscription, options, schema, COMPLETE status, valid TTL and exemptions must match
- Resolve confirmations before review — all topics require current evidence-bound answers; unknowns block. See inline resolution
What ships with it
19 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.
- references/baseline-check.md 2.7 KB
- references/discover-output.md 4.5 KB
- references/effect-classification.md 5.3 KB
- references/inline-resolution-gate.md 12 KB
- references/l0-envelope.md 6.2 KB
- references/policy-override-pattern.md 1.8 KB
- references/reconciliation-disposition.md 10 KB
- references/resume-checks.md 3.1 KB
- references/schema.md 6.2 KB
- references/terminal-commands.md 6.4 KB
- scripts/discover.py 52 KB runs code
- scripts/fixtures/README.md 207 B
- scripts/governance_baseline.py 2.4 KB runs code
- scripts/render_cached_governance.py 8.6 KB runs code
- scripts/render_governance.py 30 KB runs code
- scripts/test_discover.py 63 KB runs code
- scripts/test_governance_baseline.py 992 B runs code
- scripts/test_render_governance.py 39 KB runs code
- scripts/test_signature_parity.py 5.8 KB runs code
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.
- 23d ago First seen · 163 lines · 89 tokens per session scan A 606163cc6284
apex-azure-governance-discovery is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,853 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
cloud-solution-architect
Design well-architected Azure cloud systems — 10 design principles, 6 architecture styles, 44 design patterns, technology choices, WAF pillars.
bicep-avm-mastery
Azure Verified Modules (AVM), Bicep best practices, and MCP-powered infrastructure as code for Azure.
foundry-agent-platform
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns.
sse-streaming
POST-based Server-Sent Events streaming for Azure Functions — HTTP streaming, chunked response parsing, reconnection.