succubus

A coordination guide for multiple AI agents working in the same project. It uses a shared task board and temporary file locks so agents can identify themselves and avoid editing the same files at the same time.

In plain words
What is it for?
Use it at the start of a shared coding session, before editing files, and when handing work or file ownership to another agent.
Why use it?
It reduces conflicting changes and keeps parallel agents aware of the current plan, assigned work, and files in use.

Skill for Claude CodeCodex

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 skills/enowdev/succubus/succubus
Any agent
npx skills add enowdev/succubus --skill succubus
Clone the repo
git clone --depth 1 https://github.com/enowdev/succubus

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 923 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00062 $0.00923
Opus 5 $0.00031 $0.00462
Sonnet 5 $0.00012 $0.00185
Haiku 4.5 $0.00006 $0.00092

Measured 2d ago against content hash 45e073a5902f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

succubus 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • succubus — 100% identical, 0 lines differ
.agents/skills/succubus/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

succubus — working alongside other agents

Several AI agents may be working in this repository right now. succubus is the shared record of who is here, what the plan is, which tasks are taken, and which files are locked.

Do this first

Call succubus_register. It returns the name you are known by here — for example ORION. That name is your identity in this project: use it when referring to yourself, and when other agents refer to you.

The response also contains the current state: the active plan, your tasks, the other agents present, and the files they hold. Read it before you plan anything.

If you have forgotten your name — after a long session, or a context compaction — call succubus_whoami.

Before you edit any file

Call succubus_claim_files with the paths you are about to change.

  • Granted — go ahead. Call succubus_release_files when you are done.
  • Denied — another agent holds that file. Do not edit it. Work on something else, or leave the holder a note with succubus_handoff.

Claims expire on their own, so a crashed agent never blocks a file forever. You do not need to worry about cleaning up after someone else.

To check availability without taking a lock, use succubus_check_files.

Plan before you build

If there is no active plan and the work is not trivial, write one first with succubus_plan_create — what you are building and the approach you intend to take. Every agent reads the active plan on every turn, so this is the cheapest way to keep four sessions pointed the same direction.

Keep it current with succubus_plan_update as the approach changes. A stale plan is worse than none, because agents act on it.

Working on tasks

The board is only useful if it reflects what is happening now, so write to it as you work rather than afterwards.

  • succubus_task_create — record work as you identify it, before doing it. An unrecorded task is one another agent may start in parallel.
  • succubus_task_list — check the board before inventing new work; the task may already exist.
  • succubus_task_claim — take ownership so no one else starts the same thing.
  • succubus_task_updatein_progress when you begin, review or done when you finish. Never leave a task in in_progress that you have stopped working on: it tells every other agent a lie.

Read the full file on GitHub · 87 lines

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 · 87 lines · 62 tokens per session scan A 45e073a5902f

Subscribe to this mod's changes

succubus is a skill published in the GitHub repository enowdev/succubus (17 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 923 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

pipeline-conductor

Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call, verify claimed greens independently, intervene when a worker loops…

kirodotdev/KiroCrew · 121 tokens

coworker

Reference for the Coworker file-queue automation system: task lifecycle, directory state machine, PowerShell workers, scheduler configuration, and operational conventions. Use when you need to understand how Coworker works or debug its behavior.

platonai/Browser4 · 50 tokens

rove

Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.

Sma1lboy/rove · 56 tokens

agent-delegate

Delegate tasks to other agents in the team by creating real PaperClip child issues. Covers single-agent delegation and multi-agent coordination, with failure handling and idempotency. Trigger phrases: any task outside your direct capabilities (email/calendar/drive) that should be routed to Coder, Infrastructure…

mrobinson2/AzureAgentForge · 111 tokens

bmad-register-skill

Register a custom BMM-dependent skill in the governance registry (bmad/config/bmm-dependencies.csv). Use when the user says "register my skill", "register custom skill", "register bmm dependency", "/bmad-register-skill", or when responding to a convoke-doctor "unregistered-custom-skill" warning with intent to register.

amalik/convoke-agents · 78 tokens