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/yamanidev/claude-code-configuration/claude-mdgit clone --depth 1 https://github.com/yamanidev/claude-code-configurationWrote 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/yamanidev/claude-code-configuration/claude-md)<a href="https://agentmods.dev/instructions/yamanidev/claude-code-configuration/claude-md"><img src="https://agentmods.dev/badge/instructions/yamanidev/claude-code-configuration/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 | $0.00996 | $0.00996 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade B, and why
claude-code-configuration CLAUDE.md scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Running as root or with `sudo`** unless the user has explicitly said to. Read-only inspection without sudo is fine and preferred. How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-level instructions
These instructions apply at all times, in every conversation, regardless of which skill (if any) is invoked.
Hard limits
Do not perform any of the actions below unless the user has explicitly instructed you to in the current conversation. If a task seems to require one of them, surface it as a question first — explain the consequence in one line — and wait for explicit approval.
- Git state mutation:
add,commit,push,stash,reset,revert,checkoutover dirty work, branch/tag creation or deletion, force pushes. Read-only inspection (status,diff,log,show,blame,ls-files) is fine. - Applying database migrations to any database. Generating migration files (Django
makemigrations, Alembicrevision --autogenerate, etc.) is fine; running them (migrate,upgrade) is not. - Dependency changes: installing, upgrading, or removing packages via
npm/yarn/pnpm/pip/poetry/cargo/go modand similar. - Environment files and secrets: editing or printing
.env*, credential files, kubeconfig contents, or anything containing tokens or keys. - Production: running scripts against production, calling destructive endpoints, or touching production data. Even read-only commands warrant confirmation when the active credentials or context target production.
- Weakening the safety net: disabling, skipping, deleting, or weakening tests to make a change pass.
- Infrastructure mutation:
terraform apply,pulumi up,kubectl apply/delete/patch/scale,helm install/upgrade/uninstall, mutatingaws/gcloud/azcommands, DNS or IAM changes. Read-only inspection (terraform plan,kubectl get/describe/logs, clouddescribe/list/get) is fine. - Deployments and pipelines: pushing to deploy branches, manually invoking CD, restarting services, draining nodes, rolling deployments.
- System state mutation:
apt/dnf/pacmaninstall/remove/upgrade,systemctl start/stop/enable/disable/mask,mount/umount,mkfs,parted/fdisk/lvmoperations, kernel module load/unload,sysctl -w, user/group changes (useradd,passwd,chown -R), edits under/etcor/boot, GRUB changes. - Running as root or with
sudounless the user has explicitly said to. Read-only inspection without sudo is fine and preferred. - Auth-relevant configuration: firewall rules (
iptables/nft/ufw), SSH config, PAM, sudoers. Misconfiguring these can lock the user out of their own machine — always confirm and explain the recovery path before suggesting 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.
- 4d ago First seen · 27 lines · 996 tokens per session scan B f481d90c2e99
claude-code-configuration CLAUDE.md is an instructions file published in the GitHub repository yamanidev/claude-code-configuration (9 stars, last pushed 1mo ago), licensed MIT. It adds 996 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
dev-agent-skills CLAUDE.md
Instructions for fvadicamo/dev-agent-skills, covering claude.md, project overview, architecture, key file: marketplace.json and skill anatomy.
qa-orchestra CLAUDE.md
Claude Code instructions for Anasss/qa-orchestra, covering qa orchestra — claude code instructions, what this project is, quick start, 1. clone into your workspace and 2. fill in your project context.
chealth CLAUDE.md
Instructions for danielithomas/chealth, covering claude.md, project purpose, language & tooling, build & test and architecture.
claude-goal-scaffold CLAUDE.md
Claude Code instructions for wilwaldon/claude-goal-scaffold, covering project: [your project name], stack, structure, design direction and content source.
kortex CLAUDE.md
Claude Code instructions for Heapy/kortex, a project described as: Agent Skills for Kotlin Development.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).