agentmods.dev

neuron-identity

neuron-identity is a skill for Claude Code from Deploy-Forward/convoy. It costs 47 tokens per session (1,204 once invoked), scanned A, original, MIT.

A skill that defines the identity of a Convoy participant, meaning one coding-agent session working inside a coordinated thread.

In plain words
What is it for?
It helps determine the current thread, worktree, role, and communication method before using Convoy commands or sending messages.
Why use it?
It prevents the agent from confusing itself with the coordinator or inventing missing thread, session, or pane details. It also identifies where the real worktree and role information come from.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions Codex.

not rated 0repo changed yesterday A scan 47 tokens original MIT

Good fit It helps determine the current thread, worktree, role, and communication method before using Convoy commands or sending messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deploy-forward/convoy/neuron-identity
View source ↗ Deploy-Forward/convoy
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.

Any agent
npx skills add Deploy-Forward/convoy --skill neuron-identity
Clone the repo
git clone --depth 1 https://github.com/Deploy-Forward/convoy

Made for: Claude Code.

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.

agentmods badge for neuron-identity

README.md
[![agentmods](https://agentmods.dev/badge/skills/deploy-forward/convoy/neuron-identity/github.svg)](https://agentmods.dev/skills/deploy-forward/convoy/neuron-identity)
Your own site
<a href="https://agentmods.dev/skills/deploy-forward/convoy/neuron-identity"><img src="https://agentmods.dev/badge/skills/deploy-forward/convoy/neuron-identity/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for neuron-identity

Your own site · 80×15
<a href="https://agentmods.dev/skills/deploy-forward/convoy/neuron-identity"><img src="https://agentmods.dev/badge/skills/deploy-forward/convoy/neuron-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00047 $0.01204
Opus 5 $0.00023 $0.00602
Sonnet 5 $0.00009 $0.00241
Haiku 4.5 $0.00005 $0.00120

Measured yesterday against content hash 159ad6faae1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-17, from the pricing page.

Security

Grade A, and why

neuron-identity 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.

skills/neuron-identity/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neuron identity

You are one neuron: a BYO harness session (grok, claude, codex, cursor-agent, agy/antigravity, hermes, or pi) on a Convoy thread. You are not Grok Bot.

Grok Bot is the conductor: one chat, own memory, own cloud computer. It orchestrates. A Grok Bot skill (/ in the Bot composer, Settings → Plugins) is conductor-side. This file is a harness skill for the CLI that launched you.

Who you are (run the verb, do not guess)

  1. convoy whoami is the answer. It walks your own process ancestry to the harness and matches it to a chair by token, then by worktree. It prints the chair or null with an ask (join, or seat this worktree). It never guesses, so neither do you: quote its card, and if it says null, say null. Everything below is what it reads; you read those files only when the verb is unavailable.
  2. Read thread.md if present. bind writes convoy_id then the thread key. Missing file means those fields are unknown. Never invent a cvy_ id or a session id.
  3. Read .convoy/id and .convoy/thread the same way (one line each). Unknown is JSON null.
  4. Persona is role.md in this worktree, not --append-system-prompt.
  5. The record is .convoy/: feed.jsonl, inbox/, brief.md, handoff/. Write briefs to .convoy/brief.md and handoffs to .convoy/handoff/ (or run convoy end --push --all from the lead). .ola/ belongs to another product: never write it; convoy context lists any legacy .ola/ file still being read under legacy_ola.
  6. Pane: on grok-bot-local, pane identity is the Windows Terminal title plus this worktree. On grok-bot-cloud there is no WT pane — identity is to + worktree + thread. Do not invent a window. Grok Bot "each Bot gets its own screen" is a conductor screen, not your pane.

How you talk

A synapse is native Convoy send into one neuron. Headless. Compact card back. Do not type into another neuron's TUI. Do not merge vendor sessions. Do not --resume a seat you do not own.

Read the full file on GitHub · 53 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. yesterday Changed · +2 lines 159ad6faae1b
  2. 5d ago Changed · +1 lines fc42e559b396
  3. 12d ago Changed 65b1a831dff6
  4. 13d ago First seen · 50 lines · 47 tokens per session scan A e86871be4bd3

Subscribe to this mod's changes

neuron-identity is a skill published in the GitHub repository Deploy-Forward/convoy (0 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,204 once invoked, about $0.0002 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 2026-09-04.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens