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/trpc-group/trpc-agent-go/agents-mdgit clone --depth 1 https://github.com/trpc-group/trpc-agent-goWrote 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/trpc-group/trpc-agent-go/agents-md)<a href="https://agentmods.dev/instructions/trpc-group/trpc-agent-go/agents-md"><img src="https://agentmods.dev/badge/instructions/trpc-group/trpc-agent-go/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 | $0.01602 | $0.01602 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
trpc-agent-go 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
tRPC-Agent-Go is a Go multi-module framework for building AI agent systems. It
is not a standalone application and does not have a single root main.go.
The root module path is:
trpc.group/trpc-go/trpc-agent-go
The root module requires Go 1.21. Some independent modules, including modules
under test/, require newer Go toolchains.
Engineering principles
Preserve syntax, semantic, behavioral, serialization, persistence, and protocol compatibility unless the task explicitly requires a documented change.
Prefer minimal, focused changes. Avoid unrelated refactoring and avoid creating new abstractions before their responsibility and ownership are clear.
New behavior should preserve existing defaults and should be opt-in when practical.
Framework abstractions should be capability-oriented. Keep implementation-specific concepts in their owning packages unless their semantics are genuinely shared across implementations.
Update documentation and examples whenever public behavior, defaults, configuration, or recommended usage changes.
Go design conventions
Follow Effective Go and the Go Code Review Comments, while preserving established APIs when compatibility requires it.
- Use
gofmtandgoimports. - Use short, lowercase, single-word package names, and make exported names read naturally with their package qualifier without stutter.
- Use MixedCaps and spell common initialisms consistently.
- Prefer small, consumer-oriented interfaces and concrete constructor return types. Do not add an interface for a hypothetical abstraction.
- Make zero values useful when practical; use constructors to establish invariants when necessary.
- Pass
context.Contextfirst when needed, propagate cancellation, and avoid storing contexts in structs unless the type owns that lifetime. - Keep error strings lowercase and without trailing punctuation. Preserve
causes with
%wwhen callers need them; expose inspectable errors only for a stable caller contract. - Make goroutine, channel, resource, cancellation, and shutdown ownership explicit.
- Write Godoc for exported declarations as complete sentences beginning with the declared name and describing the caller-visible contract.
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 · 212 lines · 1,602 tokens per session scan A ff861570517f
trpc-agent-go AGENTS.md is an instructions file published in the GitHub repository trpc-group/trpc-agent-go (1,763 stars, last pushed today), licensed Apache-2.0. It adds 1,602 tokens to every session, about $0.0080 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 2026-08-30.
Other instructions, from other repositories
adk CLAUDE.md
Claude Code instructions for inference-gateway/adk, covering claude.md, what this repo is, commands, architecture and server (server/).
a2a-editor CLAUDE.md
Claude Code instructions for open-resource-discovery/a2a-editor, covering claude.md, project overview, commands, development and building.
adk AGENTS.md
AGENTS.md instructions for inference-gateway/adk, covering inference gateway a2a adk, project overview, build, test, and development commands, generated files and code style.
agent-identity-discovery AGENTS.md
AGENTS.md instructions for agentcommunity/agent-identity-discovery, covering agents.md, project overview, repo structure, quickstart and build and test matrix.
agent-identity-discovery CLAUDE.md
Claude Code instructions for agentcommunity/agent-identity-discovery, covering claude.md, project overview, common commands, install and build and development.
intermind CLAUDE.md
Instructions for monkfromearth/intermind, covering claude.md, project, locked decisions (v1), resolved questions (kept here for the record) and repo layout (actual).