Borrowing it
Nothing to install: this file belongs to PBNZ/pbnz-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PBNZ/pbnz-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/PBNZ/pbnz-skillsWrote 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/pbnz/pbnz-skills/agents-md)<a href="https://agentmods.dev/instructions/pbnz/pbnz-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pbnz/pbnz-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/pbnz/pbnz-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pbnz/pbnz-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01273 | $0.01273 |
| Opus 5 | $0.00636 | $0.00636 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
pbnz-skills 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — pbnz-skills
A personal Agent Skills marketplace. Every plugin has its own canonical repository and is listed here as a reference entry — this repo holds the listing, never a copy of the plugin.
Type: collection · Tier: Core + Public + Published
This repo follows the RepoKit standard. For the conventions and the pre-commit / pre-PR
checklists, use the repo-standard skill (RepoKit:
PBNZ/repo-kit — /plugin marketplace add PBNZ/repo-kit).
START-HERE map — where things live
| What | Where |
|---|---|
| Rules and orientation for agents | this file. CLAUDE.md is a thin @AGENTS.md import |
| Resume state — where this repo was left | docs/CHECKPOINT.md |
| Decisions and rationale | docs/adr/, template docs/adr/0000-template.md |
| User-visible changes | CHANGELOG.md, Keep a Changelog format |
| The marketplace manifest — the product of this repo | .claude-plugin/marketplace.json |
| Plugin content (skills, code, plugin manifests) | not here — in each plugin's canonical repo, see ADR-0002 |
Hostnames a SKILL.md body may link to |
.github/skill-url-allowlist.txt |
| Validation scripts (Python 3.12) | scripts/ — run by the Validate workflow |
| RepoKit compliance self-check | scripts/repokit-check.ps1 |
| Local privacy guard installer (run once per clone) | scripts/install-privacy-guard.ps1 |
| CI | .github/workflows/validate.yml |
| Release automation | .github/workflows/release.yml — attaches assets on a v*.*.* tag |
| Issue and PR templates | .github/ISSUE_TEMPLATE/, .github/PULL_REQUEST_TEMPLATE.md |
| Review guidance for GitHub Copilot | .github/copilot-instructions.md |
| Contributor guide | CONTRIBUTING.md |
| Governance | LICENSE (Apache-2.0), SECURITY.md, CODE_OF_CONDUCT.md |
| Variance — tests | No test suite. The repo is configuration and prose; correctness is enforced by the validation scripts in scripts/, run on every push and PR |
| Variance — publish profile | Marketplace-only: no release-please. Publishing is bumping the version in .claude-plugin/marketplace.json + CHANGELOG.md, tagging vX.Y.Z, and pushing. See ADR-0001 |
| Variance — type overlay | The RepoKit collection overlay is an upstream stub, and this repo has no per-component subdirs — every component is a reference entry to another repo. See ADR-0002 |
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.
- 9d ago First seen · 62 lines · 1,273 tokens per session scan A 3d13b20c165e
pbnz-skills AGENTS.md is an instructions file published in the GitHub repository PBNZ/pbnz-skills (1 stars, last pushed 25d ago), licensed Apache-2.0. It adds 1,273 tokens to every session, about $0.0064 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.