Borrowing it
Nothing to install: this file belongs to reacher-z/GraphEngineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/reacher-z/GraphEngineering/main/AGENTS.mdgit clone --depth 1 https://github.com/reacher-z/GraphEngineeringWrote 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/reacher-z/graphengineering/agents-md)<a href="https://agentmods.dev/instructions/reacher-z/graphengineering/agents-md"><img src="https://agentmods.dev/badge/instructions/reacher-z/graphengineering/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/reacher-z/graphengineering/agents-md"><img src="https://agentmods.dev/badge/instructions/reacher-z/graphengineering/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00284 | $0.00284 |
| Opus 5.5 | $0.00114 | $0.00114 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
GraphEngineering 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 2mo 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.
What it actually says
Repository agent guidance
Product invariants
spec/is the canonical cross-language protocol source.- TypeScript and Python behavior must stay aligned through conformance fixtures.
- Failures are structured values or events; never silently replace them with null.
- Deterministic transforms handle plumbing; model nodes handle judgment.
- Implicit graph cycles, unbounded retries, and unbounded dynamic fan-out are invalid.
- External side effects are at-least-once and require idempotency or approval.
- Telemetry and prompt/response capture are off by default.
Ownership during parallel work
- Main/integration agent owns root configuration,
spec/,codex_plans/, andcodex_logs/. - TypeScript runtime work owns
packages/core/andpackages/runtime/. - Python runtime work owns
python/. - Platform work owns
packages/cli/,packages/mcp-server/,apps/,tools/,docs/, andexamples/when assigned.
Do not edit another lane's files without an explicit handoff. Preserve unrelated changes in the shared worktree.
Verification
- Run focused tests for every changed package.
- Public behavior requires tests and documentation.
- Never run a rewriting formatter across files owned by another task.
- Real model-provider tests are opt-in; normal tests use deterministic fakes.
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.
- 2mo ago First seen · 29 lines · 284 tokens per session scan A 1f679acab092
GraphEngineering AGENTS.md is an instructions file published in the GitHub repository reacher-z/GraphEngineering (4 stars, last pushed 16d ago), licensed MIT. It adds 284 tokens to every session, about $0.0011 per session on Opus 5.5. 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.
GraphEngineering AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| GraphEngineering AGENTS.mdreacher-z/GraphEngineering | Instructions file | 4 | 16d ago | MIT | A | 284 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |