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/hecatehq/hecate/agents-mdgit clone --depth 1 https://github.com/hecatehq/hecateWrote 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/hecatehq/hecate/agents-md)<a href="https://agentmods.dev/instructions/hecatehq/hecate/agents-md"><img src="https://agentmods.dev/badge/instructions/hecatehq/hecate/agents-md.svg" alt="Measured on agentmods" 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 | $0.08374 | $0.08374 |
| Opus 5 | $0.04187 | $0.04187 |
| Sonnet 5 | $0.01675 | $0.01675 |
| Haiku 4.5 | $0.00837 | $0.00837 |
Grade A, and why
hecate 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 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.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hecate
Open-source local AI operations console for supervised agent work. Hecate
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. Local-first here means the runtime and UI run
on the operator's machine by default, Hecate-owned state is local in local
deployments (memory / sqlite) and can use Postgres for hosted/cloud-runtime
deployments, and the gateway binds to 127.0.0.1 by default; Hecate can still
route to cloud providers and supervise external coding-agent CLIs with their own
accounts. The React operator UI is embedded via //go:embed ui/dist.
This file is the orientation entry — the codebase map, the runtime
invariants, and the gotchas that bite often. It is what an agent
(Claude Code, Codex, Cursor, or human) reaches for when starting work
on this repo. Conventions, workflow, verification, and longer-form
guidance live in docs-ai/.
Where guidance lives
| Surface | What it carries |
|---|---|
docs-ai/ |
Canonical provider-neutral agent guidance — project context, conventions, workflow, verification, task shapes, area + posture skills |
AGENTS.md (this) and ui/AGENTS.md, internal/providers/AGENTS.md |
Codebase map per area |
CLAUDE.md |
Claude Code compatibility shim importing AGENTS.md; no standalone rules |
.github/copilot-instructions.md and .github/instructions/*.instructions.md |
GitHub Copilot compatibility shims pointing back to AGENTS.md and docs-ai/ |
docs-ai/skills/README.md |
Canonical skill set used by every agent |
docs-ai/core/agent-guidance.md |
Source-of-truth policy for keeping agent guidance provider-neutral |
docs/ |
Long-form references (architecture, runtime API, events, telemetry) |
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 · 284 lines · 8,374 tokens per session scan A 0640d4240db7
hecate AGENTS.md is an instructions file published in the GitHub repository hecatehq/hecate (22 stars, last pushed 2d ago), licensed MIT. It adds 8,374 tokens to every session, about $0.0419 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
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.
studio AGENTS.md
AGENTS.md instructions for decocms/studio, covering repository guidelines, documentation philosophy, commands, development and start full dev environment (migrations + client + server).
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.
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].
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].
zypher-agent CLAUDE.md
Instructions for corespeed-io/zypher-agent, covering claude.md, development commands, code quality, architecture overview and monorepo structure.