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/deandevz/king-context/agents-mdgit clone --depth 1 https://github.com/deandevz/king-contextWhat 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 | $0.01886 | $0.01886 |
| Opus 5 | $0.00943 | $0.00943 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
king-context 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents working in the king-context repository. This file is the canonical, tool-neutral rule set. CLAUDE.md imports it and adds Claude-Code-specific guidance on top. Do not duplicate content between the two.
What this project is
King Context is a CLI-first, local-first retrieval layer for AI agents. It indexes any corpus (vendor docs, web research, architecture decisions) into a flat-file store under .king-context/ and serves it through three console scripts: kctx (search and read), king-scrape (documentation scraping pipeline), and king-research (web research pipeline). It ships as the npm installer @king-context/cli plus a Python package with four sub-packages: king_context, context_cli, llm_providers, scraper_providers.
The MCP server (king-context-server) still ships but is the legacy, secondary surface per ADR-0001. Do not frame the project, its docs, or new features around MCP.
Non-negotiable rules
- All code, comments, identifiers, documentation, commits, and PR descriptions are written in English.
- Never use em-dashes or en-dashes anywhere: code, comments, docs, READMEs, commits, PR bodies, issues. Use periods, commas, colons, or parentheses instead.
- Never mix languages in the same file. Internal architecture drafts in
.docs/may be Portuguese; everything else is English.README-pt-br.mdis the one intentionally Portuguese published file. - ADRs are created and updated only through the
kctx adrCLI: draft the markdown elsewhere, import withkctx adr new --from-file, then runkctx adr indexandkctx adr validate. Never hand-write or hand-edit files inside.king-context/adr/.
The two retrieval stacks (critical orientation)
The repo contains two parallel retrieval stacks that do not share data:
- Canonical: the CLI flat-file stack.
src/context_cli/reads and writes JSON under.king-context/docs/,.king-context/research/, and.king-context/decisions/. Search is reverse-index metadata scoring. No SQLite, no embeddings. - Legacy: the MCP SQLite stack.
src/king_context/server.py(FastMCP) plusdb.py(SQLite, FTS5, embedding rerank) withdocs.dbanddata/at the repo root. Kept as an integration layer per ADR-0001.
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 · 116 lines · 1,886 tokens per session scan A 3130413c29cb
king-context AGENTS.md is an instructions file published in the GitHub repository deandevz/king-context (52 stars, last pushed 2mo ago), licensed MIT. It adds 1,886 tokens to every session, about $0.0094 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
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.