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/outsystems/outsystems-mcp/claude-mdgit clone --depth 1 https://github.com/OutSystems/outsystems-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/outsystems/outsystems-mcp/claude-md)<a href="https://agentmods.dev/instructions/outsystems/outsystems-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/outsystems/outsystems-mcp/claude-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 | $0.03607 | $0.03607 |
| Opus 5 | $0.01803 | $0.01803 |
| Sonnet 5 | $0.00721 | $0.00721 |
| Haiku 4.5 | $0.00361 | $0.00361 |
Grade A, and why
outsystems-mcp CLAUDE.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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (and other coding agents) when working in this repository.
Supported harnesses
README.md ships an install path per harness. This table is the canonical list of what "all supported harnesses" means. Update it in the same PR that adds or drops a path.
| Harness | Skill doc | How the skill doc arrives | MCP config target | Server key |
|---|---|---|---|---|
| Claude Code | skills/outsystems/SKILL.md |
automatic, via plugin.json's skills key |
user scope, written by claude mcp add |
n/a |
| Claude Desktop | skills/outsystems/SKILL.md |
same plugin as Claude Code, installed separately via Desktop's plugin-install flow (paid plan required) | claude_desktop_config.json |
mcpServers |
| Kiro Chat | kiro/outsystems/steering/skill.md |
automatic, via the Power's steering/ directory |
~/.kiro/settings/mcp.json |
mcpServers |
| Copilot in VS Code | copilot/skill.md |
manual copy to .github/copilot-instructions.md |
.vscode/mcp.json, or the user config |
servers |
| Copilot in CLI | copilot/skill.md |
manual copy to .github/copilot-instructions.md |
~/.copilot/mcp-config.json |
mcpServers |
| Copilot in Visual Studio | copilot/skill.md |
manual download to .github/copilot-instructions.md |
<SolutionDir>\.mcp.json, or %USERPROFILE%\.mcp.json |
servers |
| Cursor App | cursor/skills/outsystems/SKILL.md |
automatic, via cursor/.cursor-plugin/plugin.json |
Team Marketplace install (Team/Enterprise plan required) | mcpServers |
| Cursor CLI | cursor/skills/outsystems/SKILL.md |
manual copy to AGENTS.md |
~/.cursor/mcp.json (global) or .cursor/mcp.json (project) |
mcpServers |
| M365 Copilot | n/a | n/a | unsupported: no custom MCP servers | n/a |
| Other assistants | SKILL.md (root) |
manual fetch, best effort | harness-specific | harness-specific |
Three traps the table encodes:
serversvsmcpServers. VS Code and Visual Studio readservers; Copilot CLI, Kiro, Claude Desktop, and Cursor CLI readmcpServers.copilot/mcp.jsoncarries both keys so each surface copies the one it needs. Writing the wrong key fails silently: the file still parses and no server appears. (Cursor also has a.vscode/mcp.json(IDE-only) that usesservers, but the CLI ignores it.)- Claude Desktop's plugin requires a paid plan. On Free, no plugin can be installed, so those users get the tools without the conventions, the confirm-before-destructive rule included. On a paid plan, installing the plugin closes this gap the same way it does for Claude Code.
- Cursor has dual paths: plugin-based (app) and file-based (CLI). Cursor App users get the plugin from their Team Marketplace (requires Team/Enterprise plan + team admin approval). Each user then configures via agent setup, which writes
~/.cursor/mcp.json. Cursor CLI users manually create~/.cursor/mcp.jsonor.cursor/mcp.jsonand useagent mcpcommands. Both paths usemcpServerskey. The two skill docs are identical, but only the App path receives one automatically, via the plugin manifest — on the CLI path it is a manual copy toAGENTS.md, so a plugin version bump does not reach CLI users at all.
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 Changed · +14 lines · +1,059 tokens per session ead46248aeb1
- 5d ago First seen · 94 lines · 2,548 tokens per session scan A f53b3c8c1eac
outsystems-mcp CLAUDE.md is an instructions file published in the GitHub repository OutSystems/outsystems-mcp (25 stars, last pushed yesterday), licensed MIT. It adds 3,607 tokens to every session, about $0.0180 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 2026-08-30.
Other instructions, from other repositories
open-plan-annotator AGENTS.md
AGENTS.md instructions for ndom91/open-plan-annotator, covering open-plan-annotator: development guide, what this is, architecture, runtime distribution and key files.
jeff AGENTS.md
AGENTS.md instructions for johanthoren/jeff, covering agents.md: jeff, model expectation, the kitchen (persona), repo = the package and the method (how the system works).
agentic-seo-skills AGENTS.md
Instructions for agencia-conversion/agentic-seo-skills, covering agentic seo — agent runtime contract, mission, six pillars, audience and delivery — web companion first.
claude-calibration CLAUDE.md
Claude Code instructions for odere-pro/claude-calibration, covering claude-calibration — plugin development, what ships, what doesn't, pointers and agent routing.
agentic-foundry AGENTS.md
AGENTS.md instructions for lukasrepublic/agentic-foundry, covering ground rules and where to learn more.
the-agency CLAUDE.md
Claude Code instructions for takoyaro/the-agency, covering the agency — working notes, adding a cast member — checklist, shipping a skill, rules that don't bend and model tiering.