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/konteks/cli/agents-mdgit clone --depth 1 https://github.com/konteks/cliWhat 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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
cli 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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Overview
Konteks is a local-first memory engine and MCP-enabled CLI for AI coding agents. It builds project-local memory artifacts under .konteks/ and exposes warm-up, recall, save, search, and forget workflows through the CLI and MCP server.
Tech Stack
- Runtime/package manager: Bun
>=1.3with Node.js>=22support. - Language: strict TypeScript, ESM modules, path alias
@/*forsrc/*. - Build/test tooling:
tsup, Bun test, Biome, Knip, andtsc --noEmit. - Formatting/linting: Biome enforces kebab-case filenames, single quotes, no semicolons unless required, organized imports, and no explicit
any.
Repository Layout
src/entrypoints/cli: CLI command registration and command handlers.src/entrypoints/mcp: MCP server, prompts, handlers, and tools.src/modules: domain logic for memory, extraction, project state, and embeddings.src/database: schema, persistence services, actions, migrations, and database utilities.src/support: shared filesystem, CLI, output, formatting, TUI, and error-log utilities.src/assets: bundled prompts, grammar registry, and ignore-rule assets.tests/features: behavior-focused test coverage for CLI, MCP, memory, extraction, and project flows.tests/supportandtests/fake: test helpers and fakes.
Common Commands
bun run dev
bun run lint
bun run check
bun run devruns the CLI fromsrc/main.ts.bun run lintruns Biome formatting/checks, Knip, and TypeScript.bun run checkruns build, lint, and tests.
Coding Guidelines
- Keep changes scoped to the relevant entrypoint, module, database, or support boundary.
- Prefer existing helpers and public APIs over new abstractions or direct database access.
- Preserve strict TypeScript behavior; do not introduce
anyor loosen compiler settings. - Keep
.konteks/local and ignored. Do not commit generated memory artifacts. - Keep project error logging best-effort and non-blocking; logging failures must not mask original CLI or MCP errors.
- Route CLI color and branded header output through
src/support/console-output; preferconsoleOutput.print(color => ...),consoleOutput.writeError(color => ...),consoleOutput.header(), andconsoleOutput.printHeader()over importing palette or banner helpers in command code. - Keep
ConsoleOutput.colorPaletteas semantic string wrappers only:dim,error,info,primary,secondary,success, andwarning. Keep raw RGB helpers, gradients, and banner-specific color logic private to console-output support modules. - Preserve rebuild semantics:
konteks rebuildrebuilds derived memory artifacts and must preserve durable memories and diary entries. - Keep ignore matching fail-safe across ecosystems unless a deliberate product change says otherwise.
- Do not reintroduce file-size caps, per-file section caps, word chunking caps, or embedding/FTS retrieval truncation in core SQLite payload handling.
- Update docs when changing user-facing CLI behavior, MCP behavior, setup steps, storage behavior, or terminology.
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 First seen · 75 lines · 1,050 tokens per session scan A 12fbc8023680
cli AGENTS.md is an instructions file published in the GitHub repository konteks/cli (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,050 tokens to every session, about $0.0052 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
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
remnic AGENTS.md
Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
Binder AGENTS.md
Instructions for mpazik/Binder, covering binder, tech stack, monorepo structure, testing and development.
vellis AGENTS.md
Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.