succubus AGENTS.md

Repository instructions for Succubus, a shared coordination record for multiple AI agents working in the same codebase.

In plain words
What is it for?
Use them to coordinate parallel work, claim files or tasks, update progress, and see what other agents are doing.
Why use it?
They reduce conflicting edits by making agents register, share plans, record tasks, and mark which files they are using.

Instructions file for CodexOpenCode

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/enowdev/succubus/agents-md
Clone the repo
git clone --depth 1 https://github.com/enowdev/succubus

Made for: Codex, OpenCode.

Per session 502 This file is loaded in full into every session.
When invoked 502 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.

ModelPer sessionOnce invoked
Fable 5 $0.00502 $0.00502
Opus 5 $0.00251 $0.00251
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 2d ago against content hash 2a4407ae74d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

succubus 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 2d 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.

AGENTS.md · 39 lines

What it actually says

Agent coordination (succubus)

Several AI agents may work in this repository at the same time. succubus is the shared record of who is here, what the plan is, and which files are taken.

Before doing anything else, call succubus_register to adopt your identity. You will be given a name (for example ORION). That name is who you are here — use it when referring to yourself and in every succubus tool call.

Then call succubus_context to read the active plan, your tasks, and the files other agents are holding.

Write to succubus as you work, not afterwards. The board is only useful if it reflects what is happening right now:

  1. Plan before building. If there is no active plan and the work is not trivial, write one with succubus_plan_create. Keep it current with succubus_plan_update when the approach changes.
  2. Record tasks as you identify them, with succubus_task_create — before doing them, not after. An unrecorded task is one another agent may start in parallel.
  3. Claim a task with succubus_task_claim before starting it, and move it with succubus_task_update: in_progress when you begin, review or done when you finish. Never leave a task in in_progress you are no longer on.
  4. Claim files with succubus_claim_files before editing, and release them with succubus_release_files when done. If a file is held by another agent, do not edit it.
  5. Record what would otherwise be lost: a decision and its reasoning with succubus_decisions, progress with succubus_report, a note for a specific agent with succubus_handoff.
  6. Ask instead of guessing. For an ambiguous requirement or a convention you cannot infer, use succubus_ask. Do not block waiting for an answer — post the question and carry on with something else.

If the succubus tools are unavailable, continue working normally — coordination is best-effort and must never block you.

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.

  1. 2d ago First seen · 39 lines · 502 tokens per session scan A 2a4407ae74d0

Subscribe to this mod's changes

succubus AGENTS.md is an instructions file published in the GitHub repository enowdev/succubus (17 stars, last pushed 1mo ago), licensed MIT. It adds 502 tokens to every session, about $0.0025 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.