Borrowing it
Nothing to install: this file belongs to ibrhr/qdoc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ibrhr/qdoc/main/AGENTS.mdgit clone --depth 1 https://github.com/ibrhr/qdocWrote 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/ibrhr/qdoc/agents-md)<a href="https://agentmods.dev/instructions/ibrhr/qdoc/agents-md"><img src="https://agentmods.dev/badge/instructions/ibrhr/qdoc/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ibrhr/qdoc/agents-md"><img src="https://agentmods.dev/badge/instructions/ibrhr/qdoc/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03453 | $0.03453 |
| Opus 5 | $0.01726 | $0.01726 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade A, and why
qdoc AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — qdoc
qdoc - Query the Docs — qdoc is a tui/cli that you or your coding agent can use to get fast, accurate, relevant, and up-to-date information about any library or framework you're using!
Build & verify
export PATH=$PATH:/usr/local/go/bin # Go 1.26.3 lives here
go build ./... # builds all packages
go vet ./...
go test ./... # runs all tests
go test -race ./...
Docs site
cd docs
npm install
npx vitepress dev # http://localhost:5173
npx vitepress build # output: docs/.vitepress/dist/
The docs site is built with VitePress v1.6+. Config at docs/.vitepress/config.ts.
Architecture
Module path: github.com/ibrhr/qdoc
main.go # CLI routing + print commands
internal/
config/
config.go # Config struct, load, save, configPath
auth/
auth.go # Token, AuthMethod interface, ProviderInfo, AuthStatus, ForProvider
token_store.go # TokenStore — disk-backed token persistence, IsExpired
device_flow.go # DeviceFlowAuth — GitHub Copilot device flow OAuth
pkce.go # PkceAuth — PKCE OAuth (OpenAI ChatGPT subscription)
provider/
provider.go # Provider, AccessMethod structs, registry, Find, ResolveClient, error types
providers.json # Provider registry data
retry/
retry.go # Shared retry Config, BackoffDelay, IsRetryableHTTP/Error
llm/
client.go # Client (OpenAI-compat), NewClient, Send(), Stream()
codex_client.go # CodexClient — OpenAI Codex Responses API (SSE stream)
prompt.go # BuildSystemPrompt()
parse.go # ParsedAction, ParseResponses()
types.go # ChatMessage, StreamDelta, Streamer interface, Config
docsource/
source.go # Source, Entry, KnownSources, Find, fetch methods, retryableHTTPGet
html.go # extractLinks, extractMainContent (unexported HTML helpers)
runner/
runner.go # Headless query runner (--no-tui, --json)
tui/
model.go # Model struct, phase/state types, constructors (New*), Init
update.go # Update + query-mode handlers + streaming pipeline
setup.go # Setup update handlers + setup view renderers
view.go # View + query-mode rendering (header, progress, content, footer)
styles.go # Theme colors + lipgloss styles + spinner
render.go # renderMarkdown, renderInlineMarkdown, wordWrap
messages.go # All tea.Msg types (docIndexMsg, streamDeltaMsg, etc.)
sessionlog/
log.go # Session logging to ~/.config/qdoc/logs/ (per-query .log files)
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 · 239 lines · 3,453 tokens per session scan A 3c7af07cfce7
qdoc AGENTS.md is an instructions file published in the GitHub repository ibrhr/qdoc (2 stars, last pushed 8d ago), licensed MIT. It adds 3,453 tokens to every session, about $0.0173 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 2026-09-05.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.