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/robotti-io/copilot-security-instructions/mcp-server.developmentgit clone --depth 1 https://github.com/Robotti-io/copilot-security-instructionsWrote 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/robotti-io/copilot-security-instructions/mcp-server.development)<a href="https://agentmods.dev/instructions/robotti-io/copilot-security-instructions/mcp-server.development"><img src="https://agentmods.dev/badge/instructions/robotti-io/copilot-security-instructions/mcp-server.development.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 | $0.00346 | $0.00346 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
copilot-security-instructions mcp-server.development.instructions.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Every behavior change MUST include a verification step (test or curl reproduction). What it actually says
MCP server development rules (this repo)
These rules apply to changes under src/ and related MCP server tests.
Core standards
- Prefer minimal diffs and incremental improvements.
- Avoid breaking existing tool names/behaviors unless explicitly intended.
- Every behavior change MUST include a verification step (test or curl reproduction).
Express / HTTP handling
- Request bodies MUST be parsed safely:
- use explicit JSON parsing middleware
- set a reasonable size limit for JSON bodies
- Validate content negotiation:
- MCP endpoints should check
Acceptheaders as appropriate for the endpoint behavior.
- MCP endpoints should check
- Error handling MUST be consistent:
- do not expose internal stack traces to clients
- return clear status codes and brief error messages
MCP tools
- Every MCP tool MUST have:
- stable tool name (choose and keep a consistent naming convention across tools)
- title + description
- zod input schema (even if empty)
- deterministic output shape
- Do not return raw secrets or dump large file contents by default.
Logging hygiene
- Do not log raw request bodies.
- If logging headers, redact authorization-like fields.
- Prefer structured logs with
sourceand request id (when available).
Testing
- Add or update tests when:
- endpoint behavior changes
- new tools are added
- error handling changes
- Tests MUST be deterministic and fast.
Output requirements for Copilot edits
When generating patches:
- Output full file contents for modified files in fenced
mdblocks. - Include a short verification checklist (commands + expected results).
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 · 48 lines · 346 tokens per session scan A 6d425b5a335e
copilot-security-instructions mcp-server.development.instructions.md is an instructions file published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 346 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
apm cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
apm architecture.instructions.md
Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.
apm cicd.instructions.md
CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.
apm encoding.instructions.md
Cross-platform encoding rules — keep all source and CLI output within printable ASCII.
apm changelog.instructions.md
Changelog format and conventions based on Keep a Changelog.
squad copilot-instructions.md
Copilot instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.