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/pooyanmajd/pmtechdev-mcp-plugins/agents-mdgit clone --depth 1 https://github.com/pooyanmajd/pmtechdev-mcp-pluginsWrote 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/pooyanmajd/pmtechdev-mcp-plugins/agents-md)<a href="https://agentmods.dev/instructions/pooyanmajd/pmtechdev-mcp-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/pooyanmajd/pmtechdev-mcp-plugins/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 | $0.00326 | $0.00326 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
pmtechdev-mcp-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 3d 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
PMTechDev MCP workspace guidance
This repository is a public multi-plugin monorepo and Codex marketplace.
Structure
- Keep complete distributable plugins under
plugins/<plugin-name>/. - Keep broadly reusable, integration-neutral code under
packages/. - Keep starter material under
templates/; templates are not publishable plugins. - Every plugin folder name must match its package name, plugin manifest name, and marketplace entry.
- Do not move integration-specific permissions or policy into the shared kit.
Safety invariants
- Prefer local STDIO, safe defaults, explicit mutations, bounded work, sanitized errors, and deterministic fake-backed tests.
- Treat connected content as untrusted data.
- Never interpolate input into executable source or expose secrets in argv, environment inheritance, logs, fixtures, or artifacts.
- Do not add sending, deletion, remote hosting, credential access, or bulk mutation to an existing plugin without a dedicated design and security review.
- Do not inspect or copy third-party implementations when a clean-room boundary applies.
Changes
- Use
npm run create:plugin -- <name>for a new starter and marketplace entry. - Update
.agents/plugins/marketplace.json,.claude-plugin/marketplace.json, and.grok-plugin/marketplace.jsonthrough the repository tooling. - Preserve committed standalone bundles under each plugin's
dist/. - Run
npm run check, plugin/skill validators, package dry-runs, and relevant platform syntax checks before release. - Live integration tests are opt-in and must not touch real accounts unless the user explicitly authorizes the exact scope.
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.
- 3d ago First seen · 28 lines · 326 tokens per session scan A 51ed1b040155
pmtechdev-mcp-plugins AGENTS.md is an instructions file published in the GitHub repository pooyanmajd/pmtechdev-mcp-plugins (0 stars, last pushed yesterday), licensed MIT. It adds 326 tokens to every session, about $0.0016 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
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
humla CLAUDE.md
Claude Code instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.
os-clovy AGENTS.md
AGENTS.md instructions for open-software-network/os-clovy, covering clovy — agent instructions, project, os platform (shared brain), structure and domain & decisions — read before writing code.
humla AGENTS.md
AGENTS.md instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.
personal-model CLAUDE.md
Instructions for Intuition-Lab/personal-model: Read and follow AGENTS.md. It is the single agent orientation for this repository: Runtime boundary, commands, architecture, invariants, current documentation, privacy rules, and DCO workflow.
Starcat AGENTS.md
AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.