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/jmcentire/kindex/claude-mdgit clone --depth 1 https://github.com/jmcentire/kindexWrote 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/jmcentire/kindex/claude-md)<a href="https://agentmods.dev/instructions/jmcentire/kindex/claude-md"><img src="https://agentmods.dev/badge/instructions/jmcentire/kindex/claude-md.svg" alt="Measured on agentmods" 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 | $0.02380 | $0.02380 |
| Opus 5 | $0.01190 | $0.01190 |
| Sonnet 5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
kindex CLAUDE.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 6d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kindex — Knowledge Graph for AI-Assisted Workflows
Kindex is a persistent knowledge graph that indexes conversations, projects, and intellectual work so that Claude Code never starts a session blind. The CLI is kin.
Running Tests
# All tests
pytest tests/ -v
# Specific module
pytest tests/test_cli.py -v
pytest tests/test_hooks.py -v
pytest tests/test_store.py -v
# With coverage
pytest tests/ --cov=kindex --cov-report=term-missing
Key File Locations
| Path | Purpose |
|---|---|
src/kindex/cli.py |
CLI entry point and all kin subcommands |
src/kindex/dream.py |
Dream cycle: fuzzy dedup, suggestion auto-apply, domain edges |
src/kindex/referent.py |
R0 referent binding: digest validation, staleness sweep, rebind |
src/kindex/snapshots.py |
Pre-merge SQLite snapshots (rotating, fail-closed) to XDG state dir |
src/kindex/dream_deep.py |
LLM-powered cluster consolidation (--deep mode only) |
src/kindex/store.py |
SQLite + FTS5 storage layer |
src/kindex/config.py |
Configuration loading and Config model |
src/kindex/graph.py |
Graph analytics (centrality, communities, bridges) |
src/kindex/retrieve.py |
Hybrid search (FTS5 + graph BFS + RRF merge) |
src/kindex/extract.py |
Knowledge extraction from text and sessions |
src/kindex/ingest.py |
Project and session ingestion pipeline |
src/kindex/sessions.py |
Session tag lifecycle (start, update, segment, resume) |
src/kindex/coordination.py |
Collab conversations (members, cursors, inject messages, resources) |
src/kindex/locks.py |
Advisory node locks (acquire, release, expiry sweep) |
src/kindex/hooks.py |
Claude Code hook handlers (prime, compact) |
src/kindex/setup.py |
System setup (Claude hooks, launchd, crontab, .kin git merge driver) |
src/kindex/kin_merge.py |
Structured 3-way union merge for .kin/index.json + .kin/code-map.json (kin merge-kin git driver) |
src/kindex/daemon.py |
Background daemon and cron cycle |
src/kindex/budget.py |
LLM spend tracking and budget enforcement |
src/kindex/vectors.py |
Vector embedding, contextual chunk indexing, reindex maintenance, and similarity search |
src/kindex/vault.py |
Markdown vault import/export |
src/kindex/models.py |
Core data models |
src/kindex/schema.py |
Database schema and migrations |
src/kindex/llm.py |
LLM provider abstraction |
tests/ |
All tests (pytest) |
~/.kindex/ |
Default data directory (SQLite DB, logs) |
~/.config/kindex/kin.yaml |
User config |
.kin/config |
Git-tracked project context and optional work policy |
.kin/index.json |
Git-tracked project graph snapshot generated by kin index |
.kin/code-map.json |
Git-tracked repo code map generated by kin export code-map |
.gitattributes |
Points .kin/index.json + .kin/code-map.json at the merge=kindex driver (auto-written by kin index) |
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.
- 6d ago First seen · 119 lines · 2,380 tokens per session scan A d483dee7a9fe
kindex CLAUDE.md is an instructions file published in the GitHub repository jmcentire/kindex (26 stars, last pushed 2d ago), licensed MIT. It adds 2,380 tokens to every session, about $0.0119 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
navegador CLAUDE.md
Instructions for ConflictHQ/navegador, covering navegador — claude context, what it is, stack, package layout and falkordb connection.
navegador AGENTS.md
Instructions for ConflictHQ/navegador, a project described as: AST + knowledge graph context engine for AI coding agents.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
tpu_performance_autoresearch_wiki AGENTS.md
AGENTS.md instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.
Waggle-mcp AGENTS.md
AGENTS.md instructions for Abhigyan-Shekhar/Waggle-mcp, covering repository agent rules, custom rules and waggle automatic memory.