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/agentcathq/agentcat-go-sdk/agents-mdgit clone --depth 1 https://github.com/agentcathq/agentcat-go-sdkWrote 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/agentcathq/agentcat-go-sdk/agents-md)<a href="https://agentmods.dev/instructions/agentcathq/agentcat-go-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/agentcathq/agentcat-go-sdk/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 | $0.01016 | $0.01016 |
| Opus 5 | $0.00508 | $0.00508 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
agentcat-go-sdk 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 — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This is a Go workspace (go.work) with three published modules plus the examples. The root module go.agentcat.com/sdk/v2 exposes its public surface in mcpcat.go, types.go, custom_event.go, context_description.go, diagnostics.go, and metadata.go, and keeps all shared logic under internal/. The two adapter modules — mcpgo/ (mark3labs/mcp-go) and officialsdk/ (modelcontextprotocol/go-sdk) — have their own go.mod, cannot import internal/ across the module boundary, and therefore consume root re-exports. Each adapter owns its Track() entry point and Options, its tools/list injection and tools/call capture path, and a get_more_tools.go that registers the optional tool.
Key internal packages: internal/constants pins the agent-facing copy, injected parameter names, wire keys, and event tags byte-for-byte against the other AgentCat SDKs; internal/handles mints, derives, extracts, and resolves task and agent handles; internal/inject is the pure, deterministic schema-injection engine (build, registries, strip, structured mirror); internal/core holds Options, Event, AgentCatInstance, and UserIdentity; internal/registry keeps a thread-safe server→AgentCatInstance map keyed by pointer address and released via runtime.AddCleanup; internal/publisher and internal/exporters fan events out; internal/logging centralizes file-backed logging to ~/agentcat.log. There is no internal/session, internal/sessionmap, or internal/testutil — v2 removed transport sessions entirely.
MIGRATION.md is the source of truth for the v1→v2 delta and the list of removed APIs; keep other docs consistent with it rather than restating it.
Build, Test, and Development Commands
Run everything from the repo root. The full gate is make check && make test-mcpgo && make test-officialsdk && make build-examples. Do not shorten it to make check && make build-examples: make check's test step is go test ./... from the root, and a root-level ./... does not reach nested modules, with or without go.work — so it runs 17 root packages and zero adapter tests. That is why test-mcpgo and test-officialsdk exist as separate targets, and why make vet iterates every module rather than calling go vet ./... once. CI (.github/workflows/ci.yml) covers the same ground in four jobs: a gofmt check, go test -race per module across a Go 1.24/stable matrix, make vet, and make build-examples. Use go test -race ./... when touching shared-memory code, and go test -v -run TestName ./path/... for a focused run. Apply make tidy only when dependencies truly change so the module files stay stable. Because go.work is gitignored, every example must also build standalone (cd examples/<x>/<y> && GOWORK=off go build .).
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 · 21 lines · 1,016 tokens per session scan A 8c1df9f491bc
agentcat-go-sdk AGENTS.md is an instructions file published in the GitHub repository agentcathq/agentcat-go-sdk (10 stars, last pushed 3d ago), licensed MIT. It adds 1,016 tokens to every session, about $0.0051 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.