vc-gin-api: Skill for Codex

.agents/skills/simple-go-api/SKILL.md

simple-go-api is a skill for Codex from bg-vc/vc-gin-api. It costs 87 tokens per session (443 once invoked), scanned A, original, MIT.

A teaching and review guide for a small Go web API built with Gin. It follows the request path from router to handler, service, and database access layer.

In plain words
What is it for?
Use it to learn how requests flow through the project, add an endpoint or field, review the code for overengineering, or complete a guided Go backend exercise.
Why use it?
It makes the existing code easier to understand and helps keep new changes small instead of adding unnecessary structure.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

This is bg-vc/vc-gin-api's own configuration. It tells Codex how to work on vc-gin-api 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 vc-gin-api configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bg-vc/vc-gin-api. 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/bg-vc/vc-gin-api/main/.agents/skills/simple-go-api/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bg-vc/vc-gin-api

Made for: Codex.

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 simple-go-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/bg-vc/vc-gin-api/simple-go-api/github.svg)](https://agentmods.dev/skills/bg-vc/vc-gin-api/simple-go-api)
Your own site
<a href="https://agentmods.dev/skills/bg-vc/vc-gin-api/simple-go-api"><img src="https://agentmods.dev/badge/skills/bg-vc/vc-gin-api/simple-go-api/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 simple-go-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/bg-vc/vc-gin-api/simple-go-api"><img src="https://agentmods.dev/badge/skills/bg-vc/vc-gin-api/simple-go-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 443 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 $0.00087 $0.00443
Opus 5.5 $0.00035 $0.00177
Sonnet 5.5 $0.00017 $0.00089
Haiku 4.5 $0.00009 $0.00044

Measured 2mo ago against content hash 76c26f14f999, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

simple-go-api 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.

.agents/skills/simple-go-api/SKILL.md · 42 lines

What it actually says

Work with the SIMPLE Go API

Understand the request

  1. Read AGENTS.md and the relevant README language.
  2. Locate the route, handler, service, DAO, model, and focused tests involved.
  3. Explain the current request path in five short steps before proposing a structural change.

Teach an existing flow

  1. Start at the route and follow real function calls; do not explain from generic Gin knowledge alone.
  2. Show where HTTP input becomes a model, where business decisions happen, and where SQL executes.
  3. Point out one Go concept at a time, using repository code as the example.
  4. End with one small exercise the learner can complete in under 30 minutes.

Extend the API

  1. Implement the smallest complete vertical slice through the existing layers.
  2. Reuse concrete constructors and existing response/error conventions.
  3. Keep SQL parameterized and keep secrets out of logs and tracked files.
  4. Avoid new packages and interfaces unless two existing implementations already need them.
  5. Keep Redis optional and outside the account/user request path unless the user explicitly changes that rule.
  6. Add a focused test for the changed behavior.

Check simplicity

Reject or simplify a change that introduces speculative layers, generic repositories, generated CRUD, a DI framework, runtime Codex dependencies, or infrastructure unrelated to the learning goal. Explain the concrete cost in files, concepts, or startup steps.

Verify and hand off

Run gofmt, go vet ./..., go test ./..., and govulncheck ./.... Report:

  • the request path that changed;
  • the behavior a learner can now observe;
  • the tests that passed;
  • one short next exercise.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 42 lines · 87 tokens per session scan A 76c26f14f999

Subscribe to this mod's changes

simple-go-api is a skill published in the GitHub repository bg-vc/vc-gin-api (24 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 443 once invoked, about $0.0003 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.

Related

simple-go-api compared with skills from other repositories

simple-go-api next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
simple-go-apibg-vc/vc-gin-apiSkill242mo agoMITA87Codex
ddd-go-backendLSTM-Kirigaya/jinhui-skillsSkill242mo agononeA98Claude Code, Codex
jwtkataras/jwtSkill2101mo agoMITA107Claude Code
jwx-guide-v4lestrrat-go/jwxSkill2.4k3d agoMITA61Claude Code
authentication-portal-apigreenpau/caddy-securitySkill2.3k10d agoApache-2.0A44Codex
configuration-authentication-cookiesgreenpau/caddy-securitySkill2.3k10d agoApache-2.0A34Codex
configuration-authenticationgreenpau/caddy-securitySkill2.3k10d agoApache-2.0A42Codex