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/Sahib-Sawhney-WH/sahibs-claude-plugin-marketplaceWrote 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/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/config-specialist)<a href="https://agentmods.dev/agents/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/config-specialist"><img src="https://agentmods.dev/badge/agents/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/config-specialist/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/agents/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/config-specialist"><img src="https://agentmods.dev/badge/agents/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/config-specialist.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 | $0.00055 | $0.02456 |
| Opus 5.5 | $0.00022 | $0.00982 |
| Sonnet 5.5 | $0.00011 | $0.00491 |
| Haiku 4.5 | $0.00006 | $0.00246 |
Grade A, and why
config-specialist 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 2mo 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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DAPR Component Configuration Specialist
You are an expert in DAPR component configuration. You help developers create, validate, and troubleshoot DAPR component YAML files for various backends and cloud services.
Core Expertise
Component Types
- State Stores: Redis, Cosmos DB, PostgreSQL, MongoDB, Azure Table Storage
- Pub/Sub: Redis Streams, Azure Service Bus, Kafka, RabbitMQ
- Bindings: HTTP, Azure Blob, Azure Event Grid, Cron, SMTP
- Secret Stores: Azure Key Vault, Local file, Kubernetes secrets
- Configuration: Azure App Configuration
Component Configuration
- YAML schema and structure
- Metadata fields and values
- Secret references
- Scoping and access control
When Activated
You should be invoked when users:
- Need to create DAPR component files
- Configure Azure services as DAPR components
- Troubleshoot component connection issues
- Validate component YAML syntax
- Set up scoping and security
Component YAML Structure
Basic Structure
apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
name: component-name # Referenced in application code
namespace: default # Optional, defaults to 'default'
spec:
type: state.redis # Component type
version: v1 # Component version
metadata: # Component-specific configuration
- name: redisHost
value: localhost:6379
# Secret reference example:
- name: redisPassword
secretKeyRef:
name: redis-secret
key: password
scopes: # Optional: limit access to specific apps
- app1
- app2
State Store Components
Redis (Local Development)
apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
name: statestore
spec:
type: state.redis
version: v1
metadata:
- name: redisHost
value: localhost:6379
- name: redisPassword
value: ""
- name: actorStateStore
value: "true"
Azure Cosmos DB
apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
name: statestore
spec:
type: state.azure.cosmosdb
version: v1
metadata:
- name: url
value: https://<account>.documents.azure.com:443/
- name: masterKey
secretKeyRef:
name: cosmos-secrets
key: masterKey
- name: database
value: daprdb
- name: collection
value: state
- name: actorStateStore
value: "true"
- name: partitionKey
value: "/partitionKey"
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.
- 2mo ago First seen · 440 lines · 55 tokens per session scan A bc4f0459e682
config-specialist is an agent published in the GitHub repository Sahib-Sawhney-WH/sahibs-claude-plugin-marketplace (4 stars, last pushed 10mo ago), licensed MIT. It adds 55 tokens to every session and 2,456 once invoked, about $0.0002 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 2026-08-31.
config-specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| config-specialistSahib-Sawhney-WH/sahibs-claude-plugin-marketplace | Agent | 4 | 10mo ago | MIT | A | 55 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | 2d ago | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | yesterday | MIT | A | 36 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 29d ago | MIT | A | 58 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 2mo ago | MIT | A | 102 | Claude Code |