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/prest/prest-mcp-adapter/copilot-instructionsgit clone --depth 1 https://github.com/prest/prest-mcp-adapterWrote 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/prest/prest-mcp-adapter/copilot-instructions)<a href="https://agentmods.dev/instructions/prest/prest-mcp-adapter/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/prest/prest-mcp-adapter/copilot-instructions.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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
prest-mcp-adapter copilot-instructions.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 5d 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
prest-mcp-adapter — agent / Copilot instructions
What this repo is
prest-mcp is a stdio → HTTP transport bridge for pREST’s /_mcp endpoint.
It is not a second MCP server. Do not add schema introspection, SQL generation, tool definitions, or pREST business logic here.
MCP client --stdio NDJSON--> prest-mcp --HTTP POST--> pREST /_mcp
Layout
| Path | Role |
|---|---|
cmd/prest-mcp/ |
Entrypoint: load config, wire HTTP client, run stdio loop |
internal/config/ |
Env: PREST_MCP_URL, PREST_MCP_TOKEN, PREST_MCP_TIMEOUT_MS |
internal/transport/ |
NDJSON stdio + HTTP forwarder |
internal/proxy/ |
Dumb request/response bridging + JSON-RPC error synthesis |
internal/logging/ |
slog → stderr only |
Hard rules
- stdout = protocol only (newline-delimited JSON-RPC). Never write logs to stdout.
- stderr = logs/diagnostics via
slog. - Fail closed on missing/invalid
PREST_MCP_URL. - Pass through pREST JSON response bodies unchanged when they are JSON objects (including HTTP 4xx JSON-RPC errors).
- Synthesize JSON-RPC errors only for parse failures, network errors, empty/non-JSON HTTP bodies.
- Notifications (no
id): forward to HTTP; write nothing to stdout. - Go version: match
go.mod(currently 1.26). Format withgofmt. Wrap errors with%w.
Validate
go build ./...
go vet ./...
gofmt -l .
make test # unit tests + overall coverage >= 80%
make coverage # COVERAGE_MIN=80 scripts/check-coverage.sh
Overall statement coverage must stay at ≥80% (make coverage).
Out of scope (v0.1+)
prest-mcp doctor, Homebrew, native prestd mcp --stdio, inventing MCP tool wrappers, Content-Length framing (use NDJSON).
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.
- 5d ago First seen · 48 lines · 513 tokens per session scan A 0e331279df18
prest-mcp-adapter copilot-instructions.md is an instructions file published in the GitHub repository prest/prest-mcp-adapter (0 stars, last pushed 1mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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
platform AGENTS.md
Instructions for qorm/platform, covering agents.md — orienting an ai agent in the qorm repo, understand it, write / edit an app, drive a live app as an agent and build & test.
tiny-go-mcp-server AGENTS.md
AGENTS.md instructions for kioie/tiny-go-mcp-server, covering agent instructions (tiny go mcp server), commands, layout, api notes and mcp tool conventions.
cursor-rules AGENTS.md
Instructions for ZanzyTHEbar/cursor-rules, covering agents.md, repo shape, commands, config and runtime gotchas and tests and fixtures.
better-auth-firestore AGENTS.md
AGENTS.md instructions for yultyyev/better-auth-firestore, covering ai assistant guidelines, quick reference, current project state, project structure and key exports.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
ken CLAUDE.md
Claude Code instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).