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/datit309/supergraph/agents-mdgit clone --depth 1 https://github.com/datit309/supergraphWhat 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 | $0.01664 | $0.01664 |
| Opus 5 | $0.00832 | $0.00832 |
| Sonnet 5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
supergraph 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supergraph — Mandatory Workflows
CRITICAL: These are MANDATORY. Not suggestions. Not optional. Every coding task MUST follow this process.
Skills
This project uses supergraph skills with /supergraph: prefix to avoid conflicts with built-in commands.
Your AI agent MUST read and follow the relevant skill before each phase.
| Skill | When to read |
|---|---|
/supergraph:scan |
Start of every session |
/supergraph:analyze |
Ambiguous scope, touching hub/bridge |
/supergraph:plan |
Before writing any code |
/supergraph:tdd |
When implementing any feature or fix |
/supergraph:execute |
When executing saved plans |
/supergraph:fix |
After all coding is complete |
/supergraph:integration |
After unit tests pass |
/supergraph:verify |
Before claiming done/ready or committing |
/supergraph:review |
Before merging or when review is needed |
/supergraph:diagnose |
Bug exists and cause is unknown |
/supergraph:serena |
Before complex refactors, cross-file symbol analysis, or type diagnostics |
/supergraph:zoom-out |
Lost in unfamiliar code, need re-orientation |
/supergraph:architecture |
Pre-refactor, onboarding, architectural planning |
/supergraph:prd |
Requirements came from conversation, not a formal spec |
/supergraph:triage |
Processing issue backlog, preparing work for automation |
/supergraph:prototype |
Approach is uncertain before planning |
/supergraph:handoff |
Agent context window exhausted or switching sessions |
/supergraph:caveman |
Long session or token budget — activate compression |
Auto Language Detection
At session start, detect project type:
pubspec.yaml→ Flutter/Dartpackage.json→ Node.js (JS/TS)composer.json→ PHP
Use the correct test/lint commands for the detected language.
Tiered Workflow — Pick the right tier FIRST
| Tier | Condition | Path |
|---|---|---|
| Micro | < 20 lines, ≤2 files, no hub/bridge, complexity <10 | /supergraph:tdd directly → /supergraph:verify (skip analyze/plan) |
| Standard | ≤5 files, clear requirement, no cross-boundary | /supergraph:analyze → /supergraph:plan (lightweight) → /supergraph:execute → /supergraph:fix → /supergraph:verify |
| Full | >5 files, ambiguous, hub/bridge, cross-boundary, or blast radius >5 | Full pipeline below |
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 · 173 lines · 1,664 tokens per session scan A ac5ec410294c
supergraph AGENTS.md is an instructions file published in the GitHub repository datit309/supergraph (21 stars, last pushed 4d ago), licensed MIT. It adds 1,664 tokens to every session, about $0.0083 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
frappe-agent AGENTS.md
Instructions for Dkm0315/frappe-agent, covering frappe agent instructions, core behavior, bench guidance, app provenance and erpnext guidance.
frappe-agent copilot-instructions.md
Instructions for Dkm0315/frappe-agent: Treat this repository as Frappe, ERPNext, and Frappe ecosystem guidance for coding agents.
frappe-agent CLAUDE.md
Instructions for Dkm0315/frappe-agent: This repository contains Codex-native plugin assets plus portable Frappe, ERPNext, and Frappe ecosystem development guidance.
diaphora-mcp AGENTS.md
Instructions for xTeardx/diaphora-mcp, covering diaphora mcp — agent instructions, mission, source map, data contract and export rules.
diaphora-mcp CLAUDE.md
Instructions for xTeardx/diaphora-mcp, covering diaphora mcp — claude code compatibility notes, project role, source map, non-negotiable data rules and large database defaults.
jig CLAUDE.md
Instructions for ramboz/jig, covering jig — ai-native dev scaffold, hot cache, project codenames / active work, key terms (one-line index — full defs via /jig:explain ) and key documents.