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/ourines/codes/claude-mdgit clone --depth 1 https://github.com/ourines/codesWhat 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 | $0.03743 | $0.03743 |
| Opus 5 | $0.01871 | $0.01871 |
| Sonnet 5 | $0.00749 | $0.00749 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade A, and why
codes CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Test Commands
go build ./cmd/codes # Build (quick check)
go build -o codes ./cmd/codes # Build named binary
go vet ./... # Lint
go test ./... -v -count=1 # Run all tests
go test ./internal/commands -run TestX # Run single test
go test ./internal/session -v # Run package tests
make build && make test # Build + smoke tests
Version injection at build time:
go build -ldflags "-X codes/internal/commands.Version=v1.0.0 -X codes/internal/commands.Commit=$(git rev-parse --short HEAD) -X codes/internal/commands.Date=$(date -u +%Y-%m-%dT%H:%M:%SZ)" -o codes ./cmd/codes
Architecture
Entry Point Routing (cmd/codes/main.go)
The root command dynamically selects behavior:
- TTY detected → launches bubbletea TUI (
internal/tui) --jsonflag → structured JSON output viainternal/output- Non-TTY → CLI fallback (
internal/commands) - Subcommand → cobra dispatches to appropriate handler
Package Responsibilities
| Package | Role |
|---|---|
internal/config |
JSON config load/save, API testing, git info extraction, project/remote CRUD |
internal/tui |
Multi-tab bubbletea TUI (Projects, Profiles, Remotes, Settings, Stats, Tasks, Workflows) |
internal/session |
Terminal session lifecycle: spawn, track via PID files, kill |
internal/remote |
SSH/SCP operations, remote codes installation, profile sync |
internal/agent |
Agent team management: daemon lifecycle, task execution, message passing, Claude subprocess orchestration |
internal/stats |
Cost tracking: JSONL session parsing, token aggregation, caching, time-range filtering |
internal/mcp |
MCP server: 44 tools over stdio + SSE (/mcp/ on HTTP port). NewSSEHandler() mounts SSE on existing HTTP mux — single port. |
internal/commands |
Cobra command definitions (cobra.go) + implementations (commands.go) |
internal/output |
JSON mode wrapper (output.JSONMode flag) |
internal/ui |
Styled CLI text output helpers |
internal/workflow |
Workflow templates: YAML store, agent team orchestration, legacy migration |
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 · 286 lines · 3,743 tokens per session scan A 221edcd0b917
codes CLAUDE.md is an instructions file published in the GitHub repository ourines/codes (11 stars, last pushed 6mo ago), licensed MIT. It adds 3,743 tokens to every session, about $0.0187 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.
Other instructions, from other repositories
mcp-server-manager CLAUDE.md
Instructions for vlazic/mcp-server-manager, covering claude.md, project overview, development guidelines, important development notes and core commands.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.