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/gopherguides/gopher-ai/agents-mdgit clone --depth 1 https://github.com/gopherguides/gopher-aiWhat 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 | $0.01309 | $0.01309 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
gopher-ai AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
For Codex, "global" means installing plugins through the Codex marketplace cache so they load in every Codex session, regardless of the working directory. This is what `install-all.sh` uses for the curl one-liner. How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project instructions for OpenAI Codex CLI.
Project Overview
gopher-ai is a Go-focused development toolkit distributed as both Claude Code plugins and Codex plugins. Each plugin bundles related skills that activate automatically or can be invoked explicitly.
The Codex plugin set currently includes go-workflow, go-dev, gopher-guides, llm-tools, go-web, and tailwind. The repo's productivity module is currently Claude-only.
Plugins
| Plugin | Description | Skills |
|---|---|---|
go-workflow |
Issue-to-PR workflow automation | start-issue, worktree, commit, create-pr, ship, address-review, review-deep, complete-issue, e2e-verify, tmux-start |
go-dev |
Go development tools and best practices | go, go-profiling-optimization, validate-skills |
gopher-guides |
Gopher Guides training materials | gopher-guides |
llm-tools |
Multi-LLM second opinions and delegation | second-opinion, gemini-image |
go-web |
Go web scaffolding (Templ + HTMX) | templui, htmx |
tailwind |
Tailwind CSS v4 tools | tailwind-best-practices |
Workflow Skills (go-workflow plugin)
Invoke explicitly with $go-workflow:<skill-name>. Codex does not resolve bare
skill names as aliases.
| Skill | Description |
|---|---|
$go-workflow:start-issue <number> |
Full issue-to-PR workflow: fetch, branch, TDD, verify, submit |
$go-workflow:worktree create <number> |
Create isolated git worktree for an issue or PR |
$go-workflow:commit |
Auto-generate conventional commit message |
$go-workflow:create-pr |
Create PR following repo template |
$go-workflow:ship |
Ship a PR: verify, push, create PR, watch CI, merge |
$go-workflow:worktree remove |
Interactively remove a single worktree |
$go-workflow:worktree prune |
Batch cleanup of completed worktrees |
$go-workflow:review-deep [PR] |
Deep code review with full PR/issue context, then fix findings |
Example Workflow
$go-workflow:start-issue 42
# Codex fetches the issue, creates a worktree, detects bug vs feature,
# guides you through TDD implementation, verifies, and creates a PR.
$go-workflow:ship
# Verifies build/tests/lint, pushes, watches CI, and merges.
$go-workflow:worktree prune
# Cleans up worktrees for closed issues.
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 · 132 lines · 1,309 tokens per session scan A 0b0d56424938
gopher-ai AGENTS.md is an instructions file published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 2d ago), licensed MIT. It adds 1,309 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
adk-go AGENTS.md
AGENTS.md instructions for google/adk-go, covering agents.md, project overview, skills, setup & core commands and definition of done.
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
kronk AGENTS.md
Instructions for ardanlabs/kronk, covering agents.md, basic rules, mcp services and manual index.
goai AGENTS.md
Instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.
cc-fleet CLAUDE.md
Instructions for ethanhq/cc-fleet, covering claude.md, what this is, coding standards (read before editing), ai attribution and build, test, run.
dive CLAUDE.md
Instructions for deepnoodle-ai/dive, covering claude.md, project overview, commands, architecture and core types.