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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/agentcathq/agentcat-go-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/agentcathq/agentcat-go-sdk/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 5.1 | $0.03078 | $0.03078 |
| Opus 5 | $0.01539 | $0.01539 |
| Sonnet 5 | $0.00616 | $0.00616 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
agentcat-go-sdk 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
AgentCat Go SDK — an analytics agent that MCP server maintainers integrate to capture usage telemetry from tool calls (arguments, responses, user intent, actor identity). It supports two MCP libraries via separate Go modules: mcpgo/ (mark3labs/mcp-go) and officialsdk/ (modelcontextprotocol/go-sdk).
This is v2. MCP 2026-07-28 removed protocol-level sessions, so v2 replaces all transport-session correlation with explicit, stateless, per-request session handles. Module paths are go.agentcat.com/sdk/v2, go.agentcat.com/sdk/mcpgo/v2, go.agentcat.com/sdk/officialsdk/v2. MIGRATION.md is the source of truth for the v1→v2 delta and the full list of removed APIs.
Build & Test Commands
make all # fmt + vet + test (default)
make test # all tests with -race
make test-mcpgo # mcpgo tests only
make test-officialsdk # officialsdk tests only
make coverage # tests + coverage HTML report
make fmt # go fmt ./...
make fmt-check # CI-style format check (fails on unformatted code)
make vet # go vet ./...
make check # fmt-check + vet + test
Run a single test: go test -v -run TestName ./path/to/package/...
This is a Go workspace (go.work) — run commands from the repo root.
Module Layout
go.work # workspace: root + mcpgo + officialsdk + examples (incl. factory)
mcpcat.go / types.go # root module — shared integration API & type aliases
custom_event.go # PublishCustomEvent (agentcat:custom)
context_description.go # default "context" parameter copy
diagnostics.go # InitDiagnostics / LogSetupComplete facade for adapters
metadata.go # AttachEventMetadata: shared tags/properties plumbing
mcpgo/ # mcp-go adapter (separate go.mod, depends on mark3labs/mcp-go)
mcpgo.go # Track() entry point, Options, hook composition via GetHooks()
list_inject.go # tools/list hook: schema injection + registry publication
call_middleware.go # tools/call middleware: resolve, strip, capture, mint back
registered_schema.go # declares mcp_session on registered output schemas
failure_hooks.go # error-path hooks so failed calls still publish
get_more_tools.go # registers the optional get_more_tools tool
extract.go / metadata.go # request metadata, EventTags/EventProperties plumbing
officialsdk/ # official go-sdk adapter (separate go.mod)
officialsdk.go # Track() entry point, Options
middleware.go # receiving middleware: resolve, strip, capture, mint back, MRTR
list_inject.go # tools/list injection + registry publication
get_more_tools.go # registers the optional get_more_tools tool
extract.go / metadata.go # request metadata, EventTags/EventProperties plumbing
internal/ # shared internals (only importable by root module)
constants/ # byte-pinned agent-facing copy, param names, wire keys, tags
handles/ # mint / derive / validate / resolve session and agent handles
inject/ # pure schema-injection engine, registries, strip, mirror
core/ # types: Options, Event, AgentCatInstance, UserIdentity
publisher/ # async event publisher with worker pool → AgentCat API
event/ # event construction, EventContext, SDK tags
exporters/ # otlp / datadog / sentry / posthog fan-out
redaction/ # applies RedactFunc / RedactEvent before publish
registry/ # server→AgentCatInstance map, released via runtime.AddCleanup
logging/ # file-backed debug logger (~/agentcat.log)
diagnostics/ # anonymized SDK setup/runtime error reporting
validation/ sanitization/ truncation/ walk/ exceptions/ # payload hygiene helpers
examples/ # runnable examples: basic + advanced per adapter, plus
# officialsdk/factory (stateless per-request Track())
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 · +107 tokens per session 24fd911cb825
- 5d ago First seen · 100 lines · 2,971 tokens per session scan A 88f9fe83380b
agentcat-go-sdk CLAUDE.md is an instructions file published in the GitHub repository agentcathq/agentcat-go-sdk (10 stars, last pushed 5d ago), licensed MIT. It adds 3,078 tokens to every session, about $0.0154 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
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.
claw-code-go CLAUDE.md
Claude Code instructions for SocialGouv/claw-code-go, covering claw-code-go and downstream consumer: iterion.