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/calque-ai/go-calque/agents-mdgit clone --depth 1 https://github.com/calque-ai/go-calqueWrote 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/calque-ai/go-calque/agents-md)<a href="https://agentmods.dev/instructions/calque-ai/go-calque/agents-md"><img src="https://agentmods.dev/badge/instructions/calque-ai/go-calque/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 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
go-calque 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 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.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Go-Calque is a streaming multi-agent AI framework implementing HTTP middleware patterns for AI data processing. The core pattern chains middleware through io.Pipe connections where each middleware runs in its own goroutine.
Setup commands
Development Environment
go mod download # Download dependencies
go build -v ./... # Build all packages
go build -v -o /dev/null ./... # Build without output (validation)
Running Tests
go test -v ./... # Unit tests
go test -v -race -coverprofile=coverage.out -covermode=atomic ./... # With coverage
go test -bench=. -benchmem ./... # Benchmarks
examples/run_integration_tests.sh # Integration tests
Code Quality
go vet ./... # Vet analysis
golangci-lint run # Linter (uses .golangci.yml config)
gofmt -s -w . # Format code
govulncheck ./... # Security scan
Complete Development Workflow
scripts/local.sh # Run build, lint, test, benchmarks
Project structure
Core Framework:
pkg/calque/flow.go- Main orchestration engine using streaming pipelinespkg/convert/- Transform structured data at flow boundaries (JSON, YAML, JSONSchema, Protobuf)pkg/calque/- HTTP-like request/response abstraction for middleware
Middleware Packages:
pkg/middleware/ai/- AI client implementations (OpenAI, Ollama, Gemini)pkg/middleware/ctrl/- Flow control (chain, batch, fallback, ratelimit)pkg/middleware/memory/- Memory management (conversation, context, store)pkg/middleware/tools/- Tool integration (registry, execute, detect)pkg/middleware/text/- Text processing and transformationspkg/middleware/inspect/- Data flow inspection with multiple adapter supportpkg/middleware/multiagent/- Multi-agent routing and consensuspkg/middleware/mcp/- Model Context Protocol implementationpkg/middleware/remote/grpc- Remote gRPC Transport implementation
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 · 106 lines · 876 tokens per session scan A 7c8e9ad0f338
go-calque AGENTS.md is an instructions file published in the GitHub repository calque-ai/go-calque (9 stars, last pushed 2d ago), licensed MPL-2.0. It adds 876 tokens to every session, about $0.0044 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
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
manifold AGENTS.md
Instructions for intelligencedev/manifold, covering go/manifold, coding conventions, project structure & module organization, package organization and dependency injection.
mcp-devtools copilot-instructions.md
Copilot instructions for sammcj/mcp-devtools, covering github copilot instructions for mcp devtools, project overview, development setup, building the project and build the server.
duragraph go.instructions.md
Instructions for Duragraph/duragraph, covering go code review instructions, project overview, strict layer rules, domain aggregate pattern and run state machine.
gitlab-mcp-server go-mcp-server.instructions.md
Best practices and patterns for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk package (v1.7.0+).
gitlab-mcp-server go.instructions.md
Instructions for writing Go code following idiomatic Go practices and community standards.