agentgram: Skill for Claude Code

.claude/skills/review-for-prod/SKILL.md

review-for-prod is a skill for Claude Code from dfradehubs/agentgram. It costs 26 tokens per session (754 once invoked), scanned A, original, MIT.

A production-readiness review for Agentgram, an application with a Go API and a Next.js web interface.

In plain words
What is it for?
Use it to inspect API and web code for logic errors, concurrency problems, authentication issues, streaming-event errors, and deployment risks.
Why use it?
It checks whether changes are correct, secure, maintainable, and safe to deploy in a system that handles live data streams and user sessions.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is dfradehubs/agentgram's own configuration. It tells Claude Code how to work on agentgram itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentgram configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dfradehubs/agentgram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dfradehubs/agentgram/main/.claude/skills/review-for-prod/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dfradehubs/agentgram

Made for: Claude Code.

Wrote 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.

agentmods badge for review-for-prod

README.md
[![agentmods](https://agentmods.dev/badge/skills/dfradehubs/agentgram/review-for-prod/github.svg)](https://agentmods.dev/skills/dfradehubs/agentgram/review-for-prod)
Your own site
<a href="https://agentmods.dev/skills/dfradehubs/agentgram/review-for-prod"><img src="https://agentmods.dev/badge/skills/dfradehubs/agentgram/review-for-prod/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.

agentmods 80×15 button for review-for-prod

Your own site · 80×15
<a href="https://agentmods.dev/skills/dfradehubs/agentgram/review-for-prod"><img src="https://agentmods.dev/badge/skills/dfradehubs/agentgram/review-for-prod.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00754
Opus 5 $0.00013 $0.00377
Sonnet 5 $0.00005 $0.00151
Haiku 4.5 $0.00003 $0.00075

Measured 10d ago against content hash 6311ab441a55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-for-prod 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 10d 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.

.claude/skills/review-for-prod/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Act as a Senior Go and Next.js Engineer, QA Lead, and Security Reviewer with experience in production-critical real-time streaming systems.

Critically review the code provided as if you were responsible for approving or blocking its production deployment in the Agentgram platform. Be direct, rigorous, and honest.

Project context

  • API (api/): Go multiplexer that proxies to remote AI agents. Emits AG-UI SSE events. Auth via Keycloak JWT. Sessions in Redis + PostgreSQL. Config YAML with ${ENV:VAR} for secrets.
  • Web (web/): Next.js 16 frontend consuming AG-UI SSE streams. Supports parallel multi-agent streaming. UI text in Spanish (es).
  • Middleware stack: SecurityHeaders → BodyLimit(1MB) → Auth → RateLimiter
  • Protocols: REST SSE, A2A JSON-RPC, ADK — all converted to AG-UI events by the proxy layer.

Evaluate

  1. Functional correctness
  • Logic errors and edge cases
  • Concurrency: goroutines, channels, mutexes (API); parallel SSE streams, AbortController (Web)
  • Proper context.Context usage: cancellation, timeouts, context.Background() for post-disconnect saves
  • AG-UI event ordering: RUN_STARTEDTEXT_MESSAGE_*RUN_FINISHED
  • Multi-agent delta calculation (calculateDelta) and context propagation correctness
  1. Code quality (anti-spaghetti)
  • Idiomatic Go: errors as values, small interfaces, table-driven tests
  • Idiomatic React/Next.js: hooks composition, state management, effect cleanup
  • SSE streaming: proper http.Flusher usage (API), EventSource/fetch stream handling (Web)
  • Functions with too many responsibilities
  • Coupling between packages (proxy/, agents/, handlers/, middleware/)
  1. Maintainability and readability
  • Clarity for a mid-level Go or Next.js developer
  • Naming conventions (Go: unexported helpers; Web: use* hooks)
  • File and package organization following existing structure
  • Fragile, duplicated, or hard-to-extend code
  1. Security
  • JWT validation: issuer, audience (clientID), expiration, JWKS rotation
  • OIDC: state (CSRF), nonce (token substitution)
  • Secrets only via ${ENV:VAR} in YAML — never hardcoded
  • Agent error sanitization (no internal details to client)
  • Input validation and body size limits
  • Redis/PostgreSQL connection security (POSTGRES_SSLMODE)

Read the full file on GitHub · 69 lines

Changes

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.

  1. 10d ago First seen · 69 lines · 26 tokens per session scan A 6311ab441a55

Subscribe to this mod's changes

review-for-prod is a skill published in the GitHub repository dfradehubs/agentgram (20 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 754 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.