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/hassanvfx/mcp-data-analysis-agent/agents-mdgit clone --depth 1 https://github.com/hassanvfx/mcp-data-analysis-agentWrote 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/hassanvfx/mcp-data-analysis-agent/agents-md)<a href="https://agentmods.dev/instructions/hassanvfx/mcp-data-analysis-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/hassanvfx/mcp-data-analysis-agent/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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade C, and why
mcp-data-analysis-agent AGENTS.md scanned grade C with 2 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl | bash` command) to install the package and configure credential-free global MCP client Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl | bash` command) to install the package and configure credential-free global MCP client How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClineFlow: OKF Knowledge Workflow
This project keeps persistent engineering context in the knowledge/ Open Knowledge Format (OKF) v0.2 bundle.
ChatGPT Codex and compatible agents
AGENTS.md is the shared instruction entry point for ChatGPT Codex, Cursor, and other compatible coding agents. Read clineflow/WORKING_WITH_CODEX.md for the Codex workflow; the same OKF knowledge contract also applies to Cline, Copilot, and Windsurf.
Task knowledge rules
- For each substantial task, create or resume
knowledge/journals/<task-name>.mdusingknowledge/journals/TASK_TEMPLATE.md. - Every task journal is an OKF concept. Keep its YAML frontmatter valid, retain
type: Engineering Journal, and updategenerated.atafter meaningful changes. - Use
status: draftwhile work is active andstatus: stablewhen it is complete. Do not addverifiedorsourcesunless they are factual. - Before starting or resuming work, search
knowledge/first. Ifdocs/journals/exists, search it too as read-only legacy context. Never create or update new work there. - Link related concepts with normal Markdown links. Update
knowledge/log.mdfor material knowledge changes.
Commit workflow
When the user asks to commit:
- Update the active
knowledge/journals/concept with the implementation summary, decisions, tests, and next steps. - Update
knowledge/log.mdif the change added or materially changed knowledge. - Run
./validate-okfand resolve validation failures. When the project has optional PyYAML available, prefer./validate-okf --strictbefore committing. - Stage the code and updated knowledge artifacts together, then create a descriptive commit.
Repository installation requests
When a user asks to install this repository, use its install.sh (or the documented GitHub
curl | bash command) to install the package and configure credential-free global MCP client
entries. It does not bootstrap, inspect, or write the caller's project. Each data-enabled project
separately creates its ignored .mcp-data-source file.
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 · 43 lines · 586 tokens per session scan C 526e5140b758
mcp-data-analysis-agent AGENTS.md is an instructions file published in the GitHub repository hassanvfx/mcp-data-analysis-agent (0 stars, last pushed 9d ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
enferno AGENTS.md
Instructions for level09/enferno, covering agents.md, framework overview, project structure, development commands and setup & installation.
pgmnemo AGENTS.md
AGENTS.md instructions for pgmnemo/pgmnemo, covering pgmnemo — agent integration guide, 1. what pgmnemo is — and the problem it solves, the problem, architectural consequences and 2. when to adopt / when not to.
second-brain AGENTS.md
AGENTS.md instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.