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/thanarak-q/graph-engineering-workflow/agents-mdgit clone --depth 1 https://github.com/Thanarak-q/graph-engineering-workflowWhat 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 | $0.00924 | $0.00924 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
graph-engineering-workflow 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository packages one portable Agent Skill. The root contains the primary artifacts:
SKILL.md— normative workflow instructions for building and verifying agent graphs.README.md— installation, usage, examples, and the Mermaid workflow diagram.references/— detail the skill loads on demand; keepSKILL.mdlean by putting templates and long schemas here.evals/— behavior cases (evals/cases/*.yaml), the expectationlexicon.md, and how to run them.scripts/check.sh— the repository checks; run before every change.adapters/,agents/— host-specific loading notes and interface metadata.CHANGELOG.md— versioned record of behavior changes and known gaps.LICENSE— MIT license terms.
There is no application source tree or build output. SKILL.md loads in full whenever the skill activates, so new detail belongs in references/ unless an agent needs it on every run.
Build, Test, and Development Commands
No build system is configured, and there is no runner that executes the behavior evals. What is
checkable is internal consistency, and scripts/check.sh checks it:
./scripts/check.sh # Links, case shape, lexicon, README/rubric sync, size, whitespace
It verifies that every relative markdown link resolves, that every eval case parses and its id
matches its filename, that every expectation token is defined in evals/lexicon.md, that the
rubric table in README.md still matches references/rubric.md row for row, that SKILL.md
stays near the always-loaded size guidance, and that git diff --check is clean. CI runs the
same script. Review the normative documents by hand as well:
cat SKILL.md # The normative document, loaded in full on activation
cat references/rubric.md # The acceptance criteria the grader scores
For installation-related changes, inspect the documented CLI commands with a dry run or the CLI’s listing mode where available; do not install globally as part of routine validation.
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 · 59 lines · 924 tokens per session scan A 02d00a78bd11
graph-engineering-workflow AGENTS.md is an instructions file published in the GitHub repository Thanarak-q/graph-engineering-workflow (5 stars, last pushed 11d ago), licensed MIT. It adds 924 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
hermes-ai-team AGENTS.md
Instructions for smfworks/hermes-ai-team, covering mission, non-negotiable values (mirror docs/00-philosophy.md), how to consume this repo, working conventions and definition of done (for the phases in this repo).
graph-engineering-architectures AGENTS.md
Instructions for Mark393295827/graph-engineering-architectures, covering graph engineering architectures - agent instructions, scope, change contract and required checks.
slack-agent-mesh AGENTS.md
AGENTS.md instructions for nickvasilescu/slack-agent-mesh, covering agents.md — onboarding for agents and their operators, what this repo is (30 seconds), run it without any credentials, connect your agent (three ways) and rules an agent author must respect.
slack-agent-mesh CLAUDE.md
Claude Code instructions for nickvasilescu/slack-agent-mesh, covering slack agent mesh, product contract, implementation constraints and key commands.
solo AGENTS.md
Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.