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 instructions/srnichols/plan-forge/bicepgit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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 | $0.01728 | $0.01728 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00346 | $0.00346 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
plan-forge bicep.instructions.md 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bicep Best Practices
File Structure
infra/
├── main.bicep ← entry point, orchestrates modules
├── main.bicepparam ← deployment parameters (per environment)
├── abbreviations.json ← resource type abbreviation lookup
├── bicepconfig.json ← linter configuration
└── modules/
├── networking.bicep
├── compute.bicep
├── storage.bicep
└── security.bicep
Parameters
// ✅ Always use @description — describe what and why
@description('The environment name, used for resource naming and tagging.')
@allowed(['dev', 'test', 'staging', 'prod'])
param environmentName string
// ✅ Enforce length constraints where naming rules apply
@description('Short workload name used in resource names. 2–8 chars.')
@minLength(2)
@maxLength(8)
param workloadName string
// ✅ @secure on all secret parameters — never surfaces in logs
@description('The admin password for the database.')
@secure()
param dbAdminPassword string
// ❌ NEVER provide a non-empty default for a @secure param
@secure()
param secret string = '' // ← only empty string is acceptable
Naming
// ✅ Use uniqueString() with a prefix for globally unique names
var storageAccountName = 'st${workloadName}${environmentName}${uniqueString(resourceGroup().id)}'
// ✅ Use template expressions for all resource names
var keyVaultName = 'kv-${workloadName}-${environmentName}-${uniqueString(resourceGroup().id)}'
// ✅ camelCase for symbolic names — never include "Name" suffix
resource keyVault 'Microsoft.KeyVault/vaults@2023-07-01' = { ... }
// ❌ NEVER hardcode resource names
resource keyVaultName 'Microsoft.KeyVault/vaults@2023-07-01' = { ... }
Resource Definitions
// ✅ Use resource properties as outputs — don't fabricate URLs
output appUrl string = appService.properties.defaultHostName
// ❌ NEVER construct URLs manually
output appUrl string = 'https://${appServiceName}.azurewebsites.net'
// ✅ Implicit dependencies via symbolic references
resource appService 'Microsoft.Web/sites@2023-01-01' = {
properties: {
serverFarmId: appServicePlan.id // ← implicit dependency
}
}
// ✅ Use existing keyword for cross-resource references
resource existingKv 'Microsoft.KeyVault/vaults@2023-07-01' existing = {
name: keyVaultName
}
// ✅ child resources via parent property — never construct child names manually
resource secret 'Microsoft.KeyVault/vaults/secrets@2023-07-01' = {
parent: keyVault
name: 'mySecret'
properties: { value: secretValue }
}
// ✅ Extract complex expressions into variables
var appServiceConfig = {
alwaysOn: environmentName == 'prod'
minTlsVersion: '1.2'
ftpsState: 'Disabled'
}
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 · 232 lines · 1,728 tokens per session scan A aa30eaa85a6a
plan-forge bicep.instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 22d ago), licensed MIT. It adds 1,728 tokens to every session, about $0.0086 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 instructions, from other repositories
dotnet-skills AGENTS.md
Instructions for managedcode/dotnet-skills, covering agents.md, purpose, solution topology, rule precedence and path and linking rules.
dotnet-skills copilot-instructions.md
Instructions for managedcode/dotnet-skills: Use AGENTS.md as the repository-wide source of truth for workflow, catalog structure, release policy, and skill maintenance rules.
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
Perigon.CLI copilot-instructions.md
Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
maf-doctor maf-deployment.instructions.md
Always-loaded production-deployment patterns for MAF 1.3.0. Auto-applies to Program.cs, DI registration files, and infra config. Covers ManagedIdentityCredential, MaxTokens caps, secret handling, OpenTelemetry wiring, and the analyzer rules that catch regressions at write time.
maf-doctor copilot-instructions.md
Instructions for joslat/maf-doctor, covering maf 1.3.0 migration — auto-loaded constraints, maf 1.3.0 — constraints & breaking changes reference, hard constraints (never violate), fan-out / fan-in rules (silent failure risk) and key breaking changes.