interlinked-setup

A setup and troubleshooting guide for Interlinked, a local guard layer that checks AI coding-agent tool calls. It also covers connecting coding tools, managing the local background service, and changing configuration.

In plain words
What is it for?
Use it to install or remove Interlinked, connect Claude Code, Codex, Copilot CLI, Gemini, or Cursor, run diagnostics, manage the local service, and configure its server or checking policy.
Why use it?
It helps keep Interlinked's hooks and guard service working, including when the service is stopped, outdated, or blocking tool calls.

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

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,849 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 $0.00122 $0.03849
Opus 5 $0.00061 $0.01924
Sonnet 5 $0.00024 $0.00770
Haiku 4.5 $0.00012 $0.00385

Measured 2d ago against content hash 5f926a4c7219, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interlinked-setup 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-setup/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

interlinked-setup — install, operate & troubleshoot the harness

Interlinked is a local, offline-first guard layer for AI coding agents. Everything lives under <repo>/.interlinked/, and a local daemon ("the harness", a Unix-socket server) evaluates every agent tool call. This skill covers turning it on, keeping the daemon healthy, configuring it, and turning it off. The remote server is optional — hooks, guard, and activity capture work with zero network.

Load this when

  • Installing Interlinked or connecting a runner (Claude Code / Codex / Copilot CLI / Gemini / Cursor).
  • interlinked doctor reports failures, or hooks are not firing / not capturing events.
  • The guard daemon is down, stale, a zombie, or tool calls are blocked with a "daemon unreachable" reason.
  • Changing the server URL, sync mode, or check-policy/operational tier.
  • Disabling or fully removing Interlinked.

Mental model

  • Per-cwd, offline-first. All state is <cwd>/.interlinked/. Two-tier config: config.json (committed, shared) + config.local.json (gitignored, personal).
  • A daemon does the work. harness start runs a background Unix-socket server. When it is up you get the full check set; when it is down the hook falls back to a small inline subset and fails closed on the dangerous stuff (destructive commands, package installs, line-cap, merge conflicts).
  • The server is optional. Auth / sync only matter for server-backed coordination (see interlinked-coordination). Skip it entirely for local-only use.

Turning it on

Command What it does When to use
bare interlinked (unconfigured repo) The harness-first setup wizard (2026-08-16): six one-line decisions — runners to hook, enforcement mode (strict — the recommended default — /lenient/balanced), review scope (diff/whole-fileguard-rules.json diff_aware.enabled), cap overrides, brownfield adopt, and dead-code posture (2026-08-17: flag default / delete instructs the agent to remove flagged dead code in the same edit / off; writes structural_checks scoped to only the dead-code checks so the rest of the family stays a separate decision; the whole-repo sweep is interlinked deadcode) — each Enter-accepts a recommended default, shows the plan, then composes enable + mode + caps set + adopt. Local-first: never asks about a server. Non-TTY: env-driven (INTERLINKED_MODE / INTERLINKED_SCOPE / INTERLINKED_ADOPT / INTERLINKED_CLIENTS). A failed step reports and continues — every step is individually re-runnable via the owning command. Ends with a posture receipt (2026-08-17): one line per thing now enforced, each naming the command that changes it. A new user's first touch; the fastest correct install.

Read the full file on GitHub · 227 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 · 227 lines · 122 tokens per session scan A 5f926a4c7219

Subscribe to this mod's changes

interlinked-setup is a skill published in the GitHub repository QuentinCody/interlinked-cli (13 stars, last pushed 14d ago), licensed MIT. It adds 122 tokens to every session and 3,849 once invoked, about $0.0006 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