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/dryvist/claude-code-plugins/agents-mdgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.01267 | $0.01267 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
claude-code-plugins 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 yesterday.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Plugins Quick Reference
Reference guide for AI assistants working with this repository.
Repository Purpose
This is a Claude Code plugins repository containing production-ready hooks for development workflows.
Available Plugins
| Plugin | Type | Tools/Commands | Purpose |
|---|---|---|---|
| ai-cli-harness-better-practices | Skill | /goal, /session-status, /handoff, /resume, /replan, /wrap-up (incl. purge-pr mode), /wrap-up-docs |
Harness-agnostic session continuity: capped goal statements, done-vs-remaining snapshots, cold-start handoffs, verify-before-trust resume, stale-plan repair, and end-of-session wrap-up. Runs without a git repository |
| ai-delegation | Skill | /delegate-to-ai, /auto-maintain, /premium-agent-orchestration, /delegate-to-router, /openrouter-models, /multi-model-review |
Route tasks to AI models, preserve premium reasoning while cheaper agents or local/free LLMs handle checkable work, and fan a plan/diff out to independent model families for adversarial review |
| codeql-resolver | Command/Skill/Agent | /resolve-codeql |
Resolve CodeQL security alerts in GitHub Actions workflows |
| config-management | Skill | /sync-permissions, /quick-add-permission |
Manage Claude and Gemini permission configs across repositories |
| content-guards | Pre/PostToolUse | Bash, Write, Edit | Token limits, markdown/README validation, webfetch guard, issue/PR backlog limits, public-repo leakage guard |
| git-guards | PreToolUse | Bash, Edit, Write, NotebookEdit | Blocks dangerous git/gh commands and file edits on main branch |
| git-workflows | Command/Skill | /sync-main, /git-flow-next, /troubleshoot-rebase, /troubleshoot-precommit, /troubleshoot-worktree, /pre-commit-architecture |
Local git sync, branching model, and rebase/pre-commit/worktree troubleshooting |
| homelab-ops | Skill | /homelab-runbooks, /proxmox-cluster-ops, /terrakube-ops, /pxe-netboot, /llm-router-ops, /workstation-offbox-backup, /dell-idrac-bmc-ops, /zfs-resumable-transfers |
Vendor/topology-neutral homelab operational runbooks: DR-node power management, DNS convergence, secrets-engine bring-up, Proxmox VE cluster operations, Terrakube operations, PXE netboot installs, LLM router operations, workstation off-box backup, Dell iDRAC BMC operations, and resumable ZFS transfers |
| github-workflows | Command/Skill | /ship, /finalize-pr, /refresh-repo, /prune-branches (incl. --sweep and --prune-stale modes), /rebase-pr, /merge-pr (incl. --squash/-s), /pr-sweep, /issue-sweep, /resolve-pr-threads, /gh-cli-patterns, /shape-issues, /trigger-ai-reviews, /github-actions-silent-failures |
GitHub PR/issue management workflows, cross-repo workspace sweep, stale-branch pruning, parallel open-PR sweep-to-zero, issue sweeps that reconcile open issues against reality, and diagnosing silent GitHub Actions failures |
| infra-orchestration | Skill | /orchestrate-infra, /sync-inventory, /test-e2e |
Cross-repo infrastructure orchestration for Terraform and Ansible |
| code-standards | Skill | /code-quality-standards, /review-standards |
Code quality standards, documentation formatting, testing philosophy, and review guidelines |
| git-standards | Skill | /git-workflow-standards, /pr-standards |
Git workflow standards, branch hygiene, PR creation guards, workaround vs fix classification, and issue linking |
| infra-standards | Skill | /infrastructure-standards |
Infrastructure standards for Proxmox, Terraform, Ansible including deployment pipeline and secrets management |
| openbao | Skill | /openbao-secrets, /openbao-dynamic-aws-creds |
OpenBao secrets access model: mint ephemeral credentials from engines instead of storing static ones; reads pre-authorized, writes human-gated; includes a concrete dynamic-AWS-STS pattern |
| pal-health | SessionStart | — | Warns on session start if PAL MCP had a recent Doppler auth failure |
| pr-lifecycle | PostToolUse | Bash | Automatically triggers /finalize-pr after gh pr create succeeds |
| process-cleanup | PostToolUse | — | Cleanup orphaned MCP server processes on session exit |
| project-standards | Skill | /claude-skill-authoring, /workspace-standards, /skills-registry |
Claude skill authoring standards, workspace management, and skills/tools registry lookup |
| script-guards | PreToolUse/UserPromptSubmit + Skill | Bash, Write, Edit, native-first |
Blocks unnecessary script/wrapper generation and supplies the native-first discovery ladder that finds the non-custom path |
| session-analytics | Skill | /token-breakdown |
Session token analytics via Splunk OTEL telemetry |
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.
- yesterday First seen · 40 lines · 1,267 tokens per session scan A dfc46293b5fa
claude-code-plugins AGENTS.md is an instructions file published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,267 tokens to every session, about $0.0063 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
claude-ruby-marketplace CLAUDE.md
Instructions for hoblin/claude-ruby-marketplace, covering claude.md, repository purpose, before editing, directory structure and versioning.
RAD-Claude-Skills AGENTS.md
Instructions for RadOrigin-LLC/RAD-Claude-Skills, covering rad claude skills, tech stack, conventions and harness boundary.
RAD-Claude-Skills CLAUDE.md
Instructions for RadOrigin-LLC/RAD-Claude-Skills, covering rad claude skills, tech stack, conventions and harness boundary.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.