What is hecate copilot-instructions.md?

Project instructions for Hecate, an open-source local console for supervising AI operations. It covers chat, queued agent tasks, approvals, projects, memory, generated files, usage, and tracing.

Use them when changing Hecate, especially its backend, agent workflows, documentation, or other areas covered by the project's shared engineering guides.

They tell coding agents where the shared engineering rules and verification requirements live, reducing inconsistent project changes.

hecate copilot-instructions.md — Instructions file for GitHub Copilot by hecatehq: Project instructions for Hecate, an open-source local con

Install

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.

agentmods

npx agentmods add instructions/hecatehq/hecate/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/hecatehq/hecate

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hecatehq/hecate/copilot-instructions.svg)](https://agentmods.dev/instructions/hecatehq/hecate/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/hecatehq/hecate/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hecatehq/hecate/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 348 This file is loaded in full into every session.

When invoked 348 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00348	$0.00348
Opus 5	$0.00174	$0.00174
Sonnet 5	$0.00070	$0.00070
Haiku 4.5	$0.00035	$0.00035

Measured 4d ago against content hash ba3e86467f9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hecate copilot-instructions.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 4d 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.

.github/copilot-instructions.md · 31 lines

What it actually says

Hecate Copilot Instructions

Hecate is an open-source local AI operations console for supervised agent work. It combines a model gateway, Hecate Chat, queued agent_loop tasks, External Agent supervision, projects, memory, approvals, artifacts, usage, and OpenTelemetry traces into one operator surface.

This file is a GitHub Copilot adapter shim. The canonical provider-neutral guidance lives in AGENTS.md and docs-ai/; read those before changing code. Do not copy long-form rules into this file.

Universal rules:

Keep changes scoped to the user request and the existing architecture.
Follow docs-ai/core/engineering-standards.md and docs-ai/core/workflow.md.
Use the relevant docs-ai/skills/*/SKILL.md for the area being changed.
Do not create Claude-, Cursor-, Codex-, or Copilot-specific copies of shared guidance.
Do not auto-commit. Suggest a Conventional Commit message when useful.
Report the verification you ran, and call out anything you could not run.

Verification starts at docs-ai/core/verification.md. Common gates:

Backend/runtime: focused go test, then go test -race -timeout 10m ./... or just test-race for broad runtime changes.
E2E: go test -tags e2e ./e2e/....
UI: cd ui && bun run typecheck && bun run test; never use bun test.
Agent docs: just agent-docs-check, just docs-format-check, and just check-links when links change.

Changes

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.

4d ago First seen · 31 lines · 348 tokens per session scan A ba3e86467f9a

Subscribe to this mod's changes

hecate copilot-instructions.md is an instructions file published in the GitHub repository hecatehq/hecate (22 stars, last pushed 2d ago), licensed MIT. It adds 348 tokens to every session, about $0.0017 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.

LLM ai ai-gateway ai-runtime mcp-client opentelemetry

bifrost AGENTS.md

AGENTS.md instructions for maximhq/bifrost, covering agents.md — bifrost ai gateway, what is bifrost?, repository layout, go workspace and build, test & dev commands.

maximhq/bifrost · 12,300 tokens

studio AGENTS.md

AGENTS.md instructions for decocms/studio, covering repository guidelines, documentation philosophy, commands, development and start full dev environment (migrations + client + server).

decocms/studio · 8,900 tokens

ai-gateway AGENTS.md

AGENTS.md instructions for ferro-labs/ai-gateway, covering agents.md, project overview, current development snapshot, public-facing wording and build, test, and run commands.

ferro-labs/ai-gateway · 21,310 tokens

litellm AGENTS.md

AGENTS.md instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].

BerriAI/litellm · 10 tokens

litellm GEMINI.md

Gemini CLI instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].