Borrowing it
Nothing to install: this file belongs to hilyfux/knowledge-graph. 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/hilyfux/knowledge-graph/main/AGENTS.mdgit clone --depth 1 https://github.com/hilyfux/knowledge-graphWrote 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/hilyfux/knowledge-graph/agents-md)<a href="https://agentmods.dev/instructions/hilyfux/knowledge-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/hilyfux/knowledge-graph/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/hilyfux/knowledge-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/hilyfux/knowledge-graph/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 | $0.00371 | $0.00371 |
| Opus 5.5 | $0.00148 | $0.00148 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
knowledge-graph 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
Project Instructions
This repository builds Knowledge Graph, a bash + jq memory layer for AI coding agents. Treat standalone/ as the packaged installer/runtime surface and keep skills/knowledge-graph/ in sync when changing shared skill or script behavior.
Knowledge Graph
- Source of truth for runtime behavior:
standalone/skills/knowledge-graph/scripts/. - Main validation command:
bash tests/test-pipeline.sh. - Installer validation:
bash -n standalone/install.sh standalone/skills/knowledge-graph/scripts/*.shand, when available,shellcheck standalone/install.sh standalone/skills/knowledge-graph/scripts/*.sh. - Durable knowledge nodes are canonical
CLAUDE.mdandSKILL.mdfiles.AGENTS.mdis only a Codex adapter and must not duplicate module knowledge. - Codex/MCP runtime should prefer
KG_PROJECT_DIRfor non-Claude scripts. Claude Code may still setCLAUDE_PROJECT_DIR. - Do not commit
.knowledge-graph/runtime data.
Knowledge Graph
- Use the bundled MCP server in .mcp.json when available: start with kg_status, then kg_query or kg_read_node before editing unfamiliar modules.
- Durable module knowledge lives in canonical CLAUDE.md and SKILL.md files. AGENTS.md is only the Codex adapter that tells Codex to read those canonical nodes through MCP.
- Runtime data lives under .knowledge-graph/ and should stay uncommitted.
- If running scripts outside Claude Code, set KG_PROJECT_DIR to this project root; Claude Code may set CLAUDE_PROJECT_DIR instead.
- Before reporting success, include concrete evidence: tests run, files checked, or MCP resources consulted.
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 · 23 lines · 371 tokens per session scan A f3a656b3a0fc
knowledge-graph AGENTS.md is an instructions file published in the GitHub repository hilyfux/knowledge-graph (21 stars, last pushed 4mo ago), licensed MIT. It adds 371 tokens to every session, about $0.0015 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 2026-08-30.
knowledge-graph AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knowledge-graph AGENTS.mdhilyfux/knowledge-graph | Instructions file | 21 | 4mo ago | MIT | A | 371 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |