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/cyvid7-darus10/claude-code-config/agents-mdgit clone --depth 1 https://github.com/Cyvid7-Darus10/claude-code-configWrote 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/cyvid7-darus10/claude-code-config/agents-md)<a href="https://agentmods.dev/instructions/cyvid7-darus10/claude-code-config/agents-md"><img src="https://agentmods.dev/badge/instructions/cyvid7-darus10/claude-code-config/agents-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 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
claude-code-config AGENTS.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 4d 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.
What it actually says
Agent Instructions
Curated setup (trimmed 2026-07-06 — full previous config in ~/.claude/backups/pre-cleanup-2026-07-06.tar.gz).
Core Principles
- Security-First — never hardcode secrets; validate all inputs
- Test-Driven — write tests before implementation
- Immutability — prefer new objects over mutation (except where language idioms differ, e.g. Go)
Available Agents
| Agent | When to Use |
|---|---|
| planner | Complex features, refactoring |
| architect | Architectural decisions |
| tdd-guide | New features, bug fixes |
| code-reviewer | After writing/modifying code |
| security-reviewer | Before commits, sensitive code |
| build-error-resolver | When build fails |
| typescript-reviewer | TypeScript/JavaScript changes |
| python-reviewer | Python changes |
| database-reviewer | Schema design, query optimization (Postgres/Supabase) |
| docs-lookup | Library/API documentation questions |
| e2e-runner | Critical user flows |
| refactor-cleaner | Dead code cleanup |
Launch independent agents in parallel.
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.
- 4d ago First seen · 29 lines · 253 tokens per session scan A d6b9c96a4af8
claude-code-config AGENTS.md is an instructions file published in the GitHub repository Cyvid7-Darus10/claude-code-config (2 stars, last pushed 2mo ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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
tweakcc AGENTS.md
AGENTS.md instructions for Piebald-AI/tweakcc, covering agents.md, development commands, build, testing and linting & formatting.
varlock AGENTS.md
AGENTS.md instructions for dmno-dev/varlock, covering project conventions, repo structure, package manager, building and scripts.
claude-code-profiles CLAUDE.md
Instructions for quinnjr/claude-code-profiles, covering claude.md, project, architecture, command interface and directory-local profiles.
code-abyss CLAUDE.md
Instructions for telagod/code-abyss, covering claude.md, project overview, commands, persona behavioral battery (opt-in eval) and ci / cd.
claude-calibration CLAUDE.md
Claude Code instructions for odere-pro/claude-calibration, covering claude-calibration — plugin development, what ships, what doesn't, pointers and agent routing.
boilerplate.md CLAUDE.md
Instructions for ds1/boilerplate.md, covering global claude code instructions, preference persistence, writing style, safety net (bypasspermissions mode is on) and project state management.