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/thunder-id/thunderid/agents-mdgit clone --depth 1 https://github.com/thunder-id/thunderidWhat 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 | $0.01195 | $0.01195 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
thunderid 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
ThunderID is a lightweight, open-source IAM stack: a Go backend (backend/) and React frontend (frontend/) in a monorepo. It provides authentication and authorization via OAuth2/OIDC, flexible orchestration flows, and individual auth mechanisms (password, passwordless, social login).
- ARCHITECTURE.md — read only for cross-cutting changes
- Build and run: Makefile and README.md
- Documentation at docs/content
Where to Look Next
Load only the guidance the task needs:
| Working on… | Read |
|---|---|
| Backend Go code | backend/AGENTS.md |
| Frontend React code | frontend/AGENTS.md |
| Documentation | docs/AGENTS.md |
| Database schema, queries, or stores | .agent/skills/db/SKILL.md |
| Browser automation / Console UI verification | .agent/skills/console/SKILL.md |
The .agent/skills/ entries above are internal guidance for developing ThunderID. Consumer-facing setup and framework-integration skills (setup-thunderid, integrate-*) live in the separate ThunderID Skills repository (installable via /plugin marketplace add thunder-id/skills) and are not used when working in this repo.
Search Hygiene
rghonors.gitignore, which already excludes build outputs,node_modules,.claude/,/coverage,tests/e2e/distribution/,.turbo, and generated API specs — don't search them.- Do not search mirror worktrees under
.claude/worktrees/(they duplicate the repo and double your results).
Validation Ladder
- Inner loop: run the smallest relevant checks for the area you touched. The scoped AGENTS files say which tests to run.
- Pre-PR gate:
make pr_checks— the authoritative gate (verify_mocks → lint → format_check → unit/frontend/integration tests → builds). - Note:
make testis backend-only (unit + integration), not full-repo validation.
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.
- 2d ago First seen · 70 lines · 1,195 tokens per session scan A ad6e32568da3
thunderid AGENTS.md is an instructions file published in the GitHub repository thunder-id/thunderid (565 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,195 tokens to every session, about $0.0060 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
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
cockroach CLAUDE.md
Claude Code instructions for cockroachdb/cockroach, covering claude.md, cockroachdb development environment, essential commands, build package ./pkg/util/log and build the tests in package ./pkg/util/log.
faker CLAUDE.md
Claude Code instructions for jaswdr/faker, covering claude.md, repository overview, core architecture, common commands and testing.
golf CLAUDE.md
Instructions for golf-mcp/golf, covering claude.md, project overview, breaking changes in golf 0.2.x, key architecture and common development commands.
gvray-admin CLAUDE.md
Instructions for gvray/gvray-admin, covering gvray admin — claude code 指南, 项目概况, 关键目录, 开发硬规则 and 按需阅读.
awesome-go copilot-instructions.md
Copilot instructions for avelino/awesome-go, a project described as: A curated list of awesome Go frameworks, libraries and software.