A workflow guide for repositories coordinated by Nexus, a command-line tool for assigning and tracking shared agent work. It defines how agents orient themselves, choose tasks, claim files, and preserve continuity.

Use it in repositories with Nexus configuration or when starting, claiming, releasing, checking, or selecting Nexus work.

It reduces conflicts when several agents work in the same repository. It also ensures agents follow the project's shared rules and do not edit unassigned files.

nexus — Skill for Claude Code and Codex by carmelyne/inkobytes-nexus

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 carmelyne/inkobytes-nexus --skill nexus

Clone the repo

git clone --depth 1 https://github.com/carmelyne/inkobytes-nexus

Made for: Claude Code, Codex.

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/skills/carmelyne/inkobytes-nexus/nexus/github.svg)](https://agentmods.dev/skills/carmelyne/inkobytes-nexus/nexus)

Your own site

<a href="https://agentmods.dev/skills/carmelyne/inkobytes-nexus/nexus"><img src="https://agentmods.dev/badge/skills/carmelyne/inkobytes-nexus/nexus/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/carmelyne/inkobytes-nexus/nexus"><img src="https://agentmods.dev/badge/skills/carmelyne/inkobytes-nexus/nexus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,381 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.01381
Opus 5.5	$0.00026	$0.00552
Sonnet 5.5	$0.00013	$0.00276
Haiku 4.5	$0.00006	$0.00138

Measured 2mo ago against content hash 563b3094129b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nexus 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 2mo 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.

skills/nexus/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nexus

Nexus CLI is the coordination engine. This skill is only the agent playbook.

If the user, repo, or hook says Nexus is active, treat this skill as mandatory workflow. It is not optional advice.

Loop

Run nexus start; set NEXUS_AGENT for your CLI, or pass --agent @agy|@claude|@codex|@gemini. Start is orientation only, not permission to edit.
Read _NEXUS_CONSTITUTION.md.
Read USER.md if present for local user preferences.
Read continuity and latest memory at session start, nexus start, or resume.
Read _NEXUS_QUEUE.md and _NEXUS_STANDUP.md.
Choose user-assigned work or nexus next @Agent; do not free-roam into Auto-flow: no.
Claim exact shared files before editing, and before reading shared non-orientation files:
```
nexus claim <path> @Agent "intent"
```
Compare the claim freshness receipt with your last read: same blob hash means your cached read is current; different or unknown means re-read before editing. Use nexus claim --show for the full file dump.
If a hook blocks access because a shared path is unclaimed, stop and claim that exact path. Do not work around the hook with another command, cached content, or manual git operation.
Work only inside the claimed surface and run focused validation.
Release each claimed tracked file through Nexus as soon as it reaches a coherent checkpoint:

nexus release <path> "short commit message"

Do not hold claims to bundle related work into a prettier feature commit. Nexus is agent-native and file-native: optimize for file availability, rollback safety, and agent throughput.

Queue Items

When adding work to _NEXUS_QUEUE.md, keep tasks dashboard-parseable and immediately actionable. Use this shape:

- [ ] TASK/@agent: Short task title
  - Id: stable-kebab-id
  - Epic: Product area or safety theme
  - Status: Ready
  - Depends on: none
  - Files: path/one.js, path/two.md
  - Affinity: cli, docs, dashboard
  - Cost: small
  - Auto-flow: yes
  - Review: approved
  - Approved by: human
  - Notes: One practical paragraph with scope, constraints, and definition of done.
  - Goal: Why this task exists, one line.
  - Outcome: What must be true when the task is complete.
  - Constraints: What the agent must not change or assume.
  - Stop If: Conditions that require stopping for human review.
  - Evidence: Tests, logs, or reports that prove completion.

Read the full file on GitHub · 92 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.

2mo ago First seen · 92 lines · 64 tokens per session scan A 563b3094129b

Subscribe to this mod's changes

nexus is a skill published in the GitHub repository carmelyne/inkobytes-nexus (5 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 1,381 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Multi-Agent Project management ai-agents cli coordination developer-tools

clawmail

Canonical joelclaw mail coordination protocol for all agents. Use when announcing work, checking inboxes, reserving files, releasing locks, handling task handoffs, triaging stale reservations, or auditing coordination quality. Triggers on: 'clawmail', 'agent mail', 'joelclaw mail', 'reserve files', 'release locks'…

joelhooks/joelclaw · 94 tokens

Codex

Mission control: create tasks, assign to an agent/team, wait for human approval, worker runs in the background, accept results.

tubecreate/tubecli · 29 tokens

squads-cli

Squads CLI — operate your squads through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.

agents-squads/squads-cli · 52 tokens

ponytail-debt

Harvest every ponytail: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or…

dmae97/omk · 99 tokens

gh

You have access to gh (GitHub CLI) for repository and project management.

agents-squads/squads-cli · 0 tokens

dos-goal-fleet

Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.

anthony-chaudhary/dos-kernel · 51 tokens