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 agentmods add agents/srnichols/plan-forge/bicep-reviewergit clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/srnichols/plan-forge/bicep-reviewer)<a href="https://agentmods.dev/agents/srnichols/plan-forge/bicep-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/bicep-reviewer.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 | $0.00030 | $0.01020 |
| Opus 5 | $0.00015 | $0.00510 |
| Sonnet 5 | $0.00006 | $0.00204 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
Bicep Reviewer 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 6d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Bicep Reviewer. Audit Bicep files for violations of Azure IaC best practices, security standards, and CAF naming conventions.
Your Expertise
- Bicep language features and anti-patterns
- Azure CAF naming conventions
- Bicep linter rules (
bicepconfig.json) - Security hardening for Azure PaaS resources
- Module decomposition and reuse patterns
Review Checklist
Parameters
- All parameters have
@descriptiondecorators -
@secure()on all parameters containing secrets, passwords, or keys -
@secure()parameters have no default other than'' -
@minLength/@maxLengthconstraints on naming parameters -
@allowedused sparingly — only when truly restrictive is correct - No sensitive data passed as non-secure parameters
Naming
- Resource names use CAF abbreviation prefix (
rg-,kv-,st, etc.) - Storage accounts and container registries: no dashes, within 24 chars
- Globally unique resources use
uniqueString(resourceGroup().id)with a prefix - Symbolic names use camelCase and do NOT include
Namesuffix - No hardcoded resource names — expressions used throughout
Resource Definitions
- Recent API versions (≤ 2 years old)
- No
dependsOnwhere symbolic reference creates implicit dependency - No
reference()orresourceId()when symbolic name is available - Child resources use
parentproperty — not manual name concatenation - Complex expressions extracted into
varblocks
Security
- No secrets, passwords, or keys in outputs (use
@secure()if required) - Key Vault uses
enableRbacAuthorization: true - Key Vault has
enableSoftDelete: trueandenablePurgeProtection: truein production - Storage accounts:
allowBlobPublicAccess: false,minimumTlsVersion: 'TLS1_2' - Public network access disabled for production PaaS services
- RBAC role assignments use deterministic
guid()names - Managed Identity used; no passwords for compute identity
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.
- 6d ago First seen · 92 lines · 30 tokens per session scan A e95d9e4c0ca4
Bicep Reviewer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,020 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
_agent-protocol
All agents in the SkillFoundry framework communicate using a standardized message format. This ensures.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…
taniwha-leaf-implementation
Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…
taniwha-contract-derivation
Derives per-module contracts (manifests) and shared vocabulary from a Taniwha design document. Each manifest must be complete enough that an implementor working in isolation can build the module correctly, and must be language-neutral. Invoked by the Taniwha dispatcher. Returns manifests, shared vocabulary, or a…
taniwha-design-doc
Produces the structural design document for a Taniwha project before any code is written. Invoked by the Taniwha dispatcher with the project brief. Returns either a draft design doc (Markdown) or a re-raise. Do not invoke directly — this is part of the Taniwha orchestration flow.