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/muratmirgun/gophers/claude-mdgit clone --depth 1 https://github.com/muratmirgun/gophersWrote 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/instructions/muratmirgun/gophers/claude-md)<a href="https://agentmods.dev/instructions/muratmirgun/gophers/claude-md"><img src="https://agentmods.dev/badge/instructions/muratmirgun/gophers/claude-md.svg" alt="Measured on agentmods" 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 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
gophers CLAUDE.md 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gophers — Claude Skill & Agent Authoring
This project authors Claude skills and agent prompts. It is not a typical application — there is no test framework, no backend, no frontend.
Project Structure
skills/ Markdown skill files (SKILL.md per skill)
agents/ Subagent prompt files (one .md per agent)
references/ Detail/example files linked from skills
scripts/ Validation, install, or packaging scripts
.claude/ AI rules framework (rules + docs + hooks)
Workflow
- Plan first. Before writing or editing a skill/agent, draft a short plan describing the trigger conditions, scope, and the artifact to produce. Get user approval.
- One artifact at a time. Each skill or agent file is a discrete deliverable. Do not bundle unrelated work.
- Write, then verify. After authoring, validate against the skill/agent standards before claiming done.
What Matters Here
Because this repo produces prompts, the relevant rule set is narrow:
- Plan-first —
.claude/rules/_mandatory/01-workflow-plan-template.md - Coding-core (applies to scripts) —
.claude/rules/core-standards/coding-core.md - Documentation standards —
.claude/rules/core-standards/documentation-standards.md - Root hygiene —
.claude/rules/general-policies/ops/root-hygiene.md - Session file tracking (no
git add -A) —.claude/rules/general-policies/ops/session-file-tracking.md - ADR principles for design decisions —
.claude/rules/core-standards/adr-principles.md
Not applicable to this repo: any rule about REST/API design, databases, migrations, React/UI, mobile responsive, Playwright/Jest, deployment, CI/CD, security (auth/JWT), test coverage thresholds.
Skill Authoring Checklist
When writing a skill (skills/<name>/SKILL.md):
- Has YAML frontmatter with
nameanddescription descriptionclearly states when the skill should be invoked (trigger conditions)- Body explains how to perform the task, not just what
- Links to
references/files for verbose detail rather than inlining - If the skill has a checklist, it is explicit and verifiable
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.
- 5d ago First seen · 59 lines · 615 tokens per session scan A 22f9c8bc2d36
gophers CLAUDE.md is an instructions file published in the GitHub repository muratmirgun/gophers (8 stars, last pushed 24d ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
diffler AGENTS.md
Instructions for jamestkelly/diffler, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
diffler CLAUDE.md
Instructions for jamestkelly/diffler, a project described as: Generate comprehension quizzes from Git branch diffs for Claude Code, OpenCode, and pull-request workflows.
turbo CLAUDE.md
Claude Code instructions for tobihagemann/turbo, covering turbo, project structure and key files.
claude-code-toolkit CLAUDE.md
Claude Code instructions for robertguss/claude-code-toolkit, covering claude.md, project overview, build commands, package a single skill for claude.ai upload and package all skills.
Assumptions AGENTS.md
Instructions for Teycir/Assumptions, covering agent instructions for this repository and assumptions skill.
bro-skills copilot-instructions.md
Copilot instructions for wedabro/bro-skills, covering copilot instructions for bro-skills, 1. supreme order, 2. bro-skills protocol, 3. language & code and 4. safety.