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/apache/tinkerpop/agents-mdgit clone --depth 1 https://github.com/apache/tinkerpopWhat 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 | $0.01548 | $0.01548 |
| Opus 5 | $0.00774 | $0.00774 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
tinkerpop 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
You are a TinkerPop developer working across the entire monorepo—code, tests, docs, and website to implement, maintain, and validate Apache TinkerPop's graph computing framework and its multi-language Gremlin ecosystem.
Primary Guidance: Agent Skills
This repository provides development guidance as an Agent Skill named
tinker-dev. If your tool supports Agent Skills, activate that skill for detailed,
task-specific instructions covering build recipes, test evaluation, coding conventions, and
reference material for each Gremlin Language Variant.
If your tool does not discover the skill automatically, run bin/agent-setup.sh --list to
see how to configure it, or bin/agent-setup.sh <agent> to set up the integration.
Planning and Memory: Beads
TinkerPop maintainers use beads (bd) for planning and as the project's long-term
memory — it records not just what changed, but why: decisions made, alternatives rejected,
directions abandoned.
If bd is installed, run bd prime at the start of a session and again after any context
compaction. It emits .beads/PRIME.md, the canonical workflow — root binding, planning
work as a dependency graph, decision capture, labels, and pin-at-merge. Follow it in
preference to tracking work in TodoWrite, TaskCreate, or a markdown plan file.
command -v bd >/dev/null && bd prime
If bd is not installed, skip it — nothing else in this repository depends on beads. Committers
can wire the workflow into their agent automatically with bin/agent-setup.sh --contributor.
Canonical Documentation
These local documents are authoritative. If this file appears to contradict them, treat them as canonical.
README.mdCONTRIBUTING.md- Developer documentation at
docs/src/dev/**
Licensing and Provenance
Apache TinkerPop is licensed under Apache License 2.0. Contributions must meet the ASF's Generative Tooling guidance. In particular:
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 · 127 lines · 1,548 tokens per session scan A e2cc380b9c9b
tinkerpop AGENTS.md is an instructions file published in the GitHub repository apache/tinkerpop (2,144 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,548 tokens to every session, about $0.0077 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
hugegraph AGENTS.md
Instructions for apache/hugegraph, covering agents.md, stack & modules, code search anchors, build and all modules.
code-graph AGENTS.md
Instructions for FalkorDB/code-graph, covering codegraph - agent instructions, architecture, data flow, directory structure and commands.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
pgGraph AGENTS.md
AGENTS.md instructions for Evokoa/pgGraph, covering package manager safety wrapper and pggraph source-of-truth principle.
code-graph CLAUDE.md
Instructions for FalkorDB/code-graph, a project described as: A code-graph demo using GraphRAG-SDK and FalkorDB.
cognee CLAUDE.md
Instructions for topoteretes/cognee, covering claude.md, project overview, development commands, setup and create virtual environment (recommended: uv).