What is kluris AGENTS.md?

Project instructions for kluris, a command-line tool that turns shared, human-curated knowledge into subject-matter guidance for AI agents.

Use them when changing kluris commands or core logic, working with the ngvoicu-sme knowledge store, installing the project for development, or running its test and coverage checks.

They show where the project's code and tests live and require the shared knowledge store to be accessed through kluris instead of edited directly.

kluris AGENTS.md — Instructions file for Codex and OpenCode by ngvoicu: Project instructions for kluris, a command-line tool that turns…

Install

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.

agentmods

npx agentmods add instructions/ngvoicu/kluris/agents-md

Clone the repo

git clone --depth 1 https://github.com/ngvoicu/kluris

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ngvoicu/kluris/agents-md.svg)](https://agentmods.dev/instructions/ngvoicu/kluris/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ngvoicu/kluris/agents-md"><img src="https://agentmods.dev/badge/instructions/ngvoicu/kluris/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,819 This file is loaded in full into every session.

When invoked 1,819 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01819	$0.01819
Opus 5	$0.00910	$0.00910
Sonnet 5	$0.00364	$0.00364
Haiku 4.5	$0.00182	$0.00182

Measured 5d ago against content hash 9a60cc5ceb4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

kluris 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 5d 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.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project: kluris

CLI tool that turns AI agents into team subject matter experts with shared, human-curated knowledge. Published to PyPI as kluris. Source: ngvoicu/kluris.

Read and write to the ngvoicu-sme brain through kluris (never edit brain files by hand). Use the /kluris-ngvoicu-sme skill — search, learn, remember, create.

Quick Reference

pip install -e ".[dev]"          # dev install
pytest tests/ -v                 # 979 tests
pytest tests/ --cov=kluris -q    # 90%+ coverage

Source Layout

All CLI commands are in src/kluris/cli.py (single file). Core logic is in src/kluris/core/ (13 modules). Agent skill and workflow templates are inline strings in src/kluris/core/agents.py. No Jinja2 templates -- dependency was removed.

Key Files

src/kluris/cli.py -- all 13 Click commands (incl. register, pack, and companion), wizard logic, KlurisGroup error handler, search + wake-up commands and collectors, _resolve_brains (picker + non-TTY guard + --brain all), _do_install (per-destination atomic stage-then-rename), _sync_brain_state (batch git log + update_frontmatter(preloaded=...))
src/kluris/core/agents.py -- AGENT_REGISTRY (9 agents, including Hermes), per-brain SKILL.md renderer (render_skill(skill_name, brain_name, brain_path, has_git, brain_description)). Every brain gets a named kluris-<name> skill, even when only one brain is registered. SKILL_BODY contains a single-brain header, Bootstrap, Query first, Intent detection (uses kluris search as the primary search path), Writing rules, and CLI commands sections. Brain paths are emitted in POSIX form via _posix_path() so bash on Windows handles them correctly.
src/kluris/core/brain.py -- BRAIN_TYPES, scaffold_brain(), _generate_readme(), validate_brain_name() (rejects reserved word all, max 48 chars)
src/kluris/core/config.py -- Pydantic models (BrainEntry, BrainConfig, GlobalConfig), config read/write, register/unregister.
src/kluris/core/maps.py -- generate_brain_md(), generate_map_md()
src/kluris/core/linker.py -- synapse validation, bidirectional checks, orphan detection, detect_deprecation_issues(), type-aware check_frontmatter()
src/kluris/core/search.py -- powers kluris search. _collect_searchable walks neurons + glossary + brain.md, _score_hit uses occurrence-count ranking, _extract_snippet is UTF-8 safe, search_brain is the public entry point.
src/kluris/core/frontmatter.py -- read_frontmatter, write_frontmatter, update_frontmatter(path, patch, *, preloaded=(meta, body)?) — the preloaded form skips the second disk read, used by dream's hot path
src/kluris/core/mri.py -- graph building, standalone HTML generation with file-browser tree sidebar in the expand modal
src/kluris/core/git.py -- subprocess git wrapper; git_log_file_dates() returns (latest_by_path, created_by_path) from one walk — replaces the per-file helpers entirely

Read the full file on GitHub · 77 lines

Changes

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.

5d ago First seen · 77 lines · 1,819 tokens per session scan A 9a60cc5ceb4a

Subscribe to this mod's changes

kluris AGENTS.md is an instructions file published in the GitHub repository ngvoicu/kluris (7 stars, last pushed 2mo ago), licensed MIT. It adds 1,819 tokens to every session, about $0.0091 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 2026-08-31.

ai-agents ai-coding claude-code claude-skills cline codex

pg-aiguide CLAUDE.md

Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).

timescale/pg-aiguide · 419 tokens

assaio AGENTS.md

AGENTS.md instructions for assaio/assaio, covering agents.md — assaio, what this is, code philosophy (non-negotiable), code standards (enforced + human-reviewed) and honesty rules (product-critical).

assaio/assaio · 2,938 tokens

assaio CLAUDE.md

Claude Code instructions for assaio/assaio, a project described as: Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugins in any…

assaio/assaio · 24 tokens

kluris AGENTS.md