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/u9401066/pharmacy-mcp/agents-mdgit clone --depth 1 https://github.com/u9401066/pharmacy-mcpWrote 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/u9401066/pharmacy-mcp/agents-md)<a href="https://agentmods.dev/instructions/u9401066/pharmacy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/u9401066/pharmacy-mcp/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 5.1 | $0.00588 | $0.00588 |
| Opus 5 | $0.00294 | $0.00294 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
pharmacy-mcp 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 6d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zotero + PubMed MCP Codex Harness
These are the workspace instructions for Codex when using Zotero Keeper and PubMed Search MCP through the VS Code extension.
Goal
Help the user search biomedical literature, inspect papers, and import selected articles into Zotero without losing provenance or overwriting user choices.
Working Style
- Use Traditional Chinese unless the user asks otherwise.
- Explain search/import steps briefly.
- Ask before importing anything into Zotero.
- Keep PubMed search/discovery/export work in PubMed Search MCP.
- Keep persistence, collection selection, and Zotero inspection in Zotero Keeper.
Core Workflow
- Start broad literature discovery with
unified_search. - Use
parse_picoandgenerate_search_queriesfor clinical or comparison questions. - Reuse session state with
get_session_pmids,get_cached_article, andget_session_summary. - Use related/citing/reference/fulltext tools for follow-up instead of rerunning the same search.
- Before saving to Zotero, call
list_collectionsunless the destination is already confirmed. - Check duplicates with
check_articles_owned. - Use
import_articlesas the default PubMed-to-Zotero handoff.
Repository Work
- Treat
.codex/skills,.claude/skills,.cline/skills, and.clinerulesas bundled assistant harness assets. - This repository is a Python package, not the Zotero Keeper VS Code extension.
- Do not run VSIX,
npm run sync-assets, orvscode-extension/**release steps unless an external extension repository is explicitly opened. - For this repository, release gates are:
uv run pytest --cov=src --cov-report=term-missinguv run ruff check src tests scriptsuv run mypy srcuv run bandit -q -r srcuv builduv run python scripts/audit_release_artifacts.py dist
- Preserve custom user
AGENTS.md, Copilot instructions, and Cline settings during assistant harness updates.
Guardrails
- Do not import into the Zotero root collection without explicit confirmation.
- Do not assume the target collection.
- Do not repeat searches when session state already contains the relevant PMIDs.
- Distinguish peer-reviewed articles, preprints, and metadata-only records.
- Keep NCBI email/API-key and institutional access settings intact.
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.
- 6d ago First seen · 58 lines · 588 tokens per session scan A 67121a45f181
pharmacy-mcp AGENTS.md is an instructions file published in the GitHub repository u9401066/pharmacy-mcp (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 588 tokens to every session, about $0.0029 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
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).
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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.