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.
curl -O https://raw.githubusercontent.com/dfradehubs/agentgram/main/.claude/skills/review-for-prod/SKILL.mdgit clone --depth 1 https://github.com/dfradehubs/agentgramWrote 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/dfradehubs/agentgram/review-for-prod)<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.
<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>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 | $0.00026 | $0.00754 |
| Opus 5.5 | $0.00010 | $0.00302 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
review-for-prod scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Act as a Senior Go and Next.js Engineer, QA Lead, and Security Reviewer with experience in production-critical real-time streaming systems.
Critically review the code provided as if you were responsible for approving or blocking its production deployment in the Agentgram platform. Be direct, rigorous, and honest.
Project context
- API (
api/): Go multiplexer that proxies to remote AI agents. Emits AG-UI SSE events. Auth via Keycloak JWT. Sessions in Redis + PostgreSQL. Config YAML with${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
- Functional correctness
- Logic errors and edge cases
- Concurrency: goroutines, channels, mutexes (API); parallel SSE streams, AbortController (Web)
- Proper
context.Contextusage: cancellation, timeouts,context.Background()for post-disconnect saves - AG-UI event ordering:
RUN_STARTED→TEXT_MESSAGE_*→RUN_FINISHED - Multi-agent delta calculation (
calculateDelta) and context propagation correctness
- 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.Flusherusage (API),EventSource/fetchstream handling (Web) - Functions with too many responsibilities
- Coupling between packages (
proxy/,agents/,handlers/,middleware/)
- 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
- 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)
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.
- 1mo ago First seen · 69 lines · 26 tokens per session scan A 6311ab441a55
review-for-prod is a skill published in the GitHub repository dfradehubs/agentgram (22 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 754 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
merge-prs
Consume analyzed PR plans, implement authorized fixes with contributor credit, validate exact candidates, and merge only owner-selected and explicitly authorized groups through the shared gates. Requires prior review evidence; unknown or failing required checks remain HOLD.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
green-prs
Inspect and prepare the selected PR queue against its exact current base, repair authorized defects with contributor credit, and report full versus partial validation. Use for maintainer pre-greening; merging requires separate owner authorization and the shared merge gates.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
pr-review
Review a GitHub pull request using multiple expert personas. Takes a PR URL as input, analyzes the changes, and generates comprehensive review feedback from different perspectives (Merge Specialist, Frontend, Backend, Security, DevOps, AI/Agent, SRE, Chief Architect).
archestra-pr-hygiene
Use when opening or updating an Archestra pull request to write an accurate conventional title and a practical, evidence-based description.