interlinked-coordination

A coordination guide for teams of AI agents and humans using Interlinked. It covers shared tasks, messages, handoffs, workspace switching, checkpoints, and file reservations.

In plain words
What is it for?
Use it to pick up or hand off tasks, message teammates, check an inbox, switch workspaces, save or restore checkpoints, reserve files, and check CI status.
Why use it?
It helps multiple workers coordinate changes and avoid editing files that another worker has reserved, with some features available offline.

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/quentincody/interlinked-cli/interlinked-coordination
Any agent
npx skills add QuentinCody/interlinked-cli --skill interlinked-coordination
Clone the repo
git clone --depth 1 https://github.com/QuentinCody/interlinked-cli

Made for: Claude Code, Codex.

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,519 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 $0.00156 $0.02519
Opus 5 $0.00078 $0.01260
Sonnet 5 $0.00031 $0.00504
Haiku 4.5 $0.00016 $0.00252

Measured 2d ago against content hash 74dcdda8581b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interlinked-coordination 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.

skills/interlinked-coordination/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

interlinked-coordination — multi-agent server surface & local checkpoints

The Interlinked CLI is a local companion; the Interlinked MCP Server is the source of truth for coordination. Two halves:

  • Server-backed (needs auth + a reachable server): tasks, send, inbox, handoff, workspace. These are thin wrappers that POST to the server; they do nothing useful offline (they short-circuit with "Not authenticated. Run: interlinked login"). (cloud recent also needs a token but via a separate cloud_governor.url. attach is not server-gated — it writes config locally and only best-effort contacts the server, so it works offline.)
  • Local-only (offline): checkpoint, rewind, resume, guard (git-hook reservation checks), reminder, ci-status, mcp stdio, and automatic file reservations among sibling agents on the same machine.

The whole server half is opt-in. Auth resolution: explicit --tokenaccess_token in config.local.json (auto-refresh) → Claude Code credentials fallback. localhost/127.0.0.1 server_url skips auth entirely (dev mode).

Load this when

  • Picking up / handing off work, messaging a peer, or checking your inbox.
  • A write was blocked/warned because a file is "reserved by" another agent.
  • Switching workspace context.
  • Creating or restoring a local checkpoint (read the git-safety warning first).
  • Installing the git-hook reservation guard, or checking CI failure rates.

⚠️ Git-safety (read before any checkpoint/rewind/resume)

checkpoint, rewind, resume, and git link-checkpoint --apply mutate git stategit stash, git checkout <sha> (detaches HEAD), git checkout -- . && git clean -fd (discards uncommitted changes + deletes untracked files), or commit amend. Under the standing rule that each commit/push/reset/stash/checkout is an independent per-turn ask, an agent must not run these autonomously — describe and recommend, don't execute, unless the user explicitly authorizes it this turn. Also note rewind rarely restores the working tree (the checkpoint stash is popped at creation, so the message-based lookup usually finds nothing) — its reliable effect is detaching HEAD to the base commit with a "changes may be missing" warning. Don't rely on it as an undo.

Read the full file on GitHub · 142 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 142 lines · 156 tokens per session scan A 74dcdda8581b

Subscribe to this mod's changes

interlinked-coordination is a skill published in the GitHub repository QuentinCody/interlinked-cli (13 stars, last pushed 14d ago), licensed MIT. It adds 156 tokens to every session and 2,519 once invoked, about $0.0008 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 2026-08-31.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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