It Operations
davila7/claude-code-templates
Manages IT infrastructure, monitoring, incident response, and service reliability.
Package, test, and operate the experimental Interlinked Cowork plugin.
MITAuto-check passed
Install Interlinked Cowork
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install QuentinCody/interlinked-cli interlinked-cowork --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/interlinked-cowork .claude/skills/interlinked-cowork && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .claude/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-coworkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install QuentinCody/interlinked-cli interlinked-cowork --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/interlinked-cowork .agents/skills/interlinked-cowork && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .agents/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install QuentinCody/interlinked-cli interlinked-cowork --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/interlinked-cowork .cursor/skills/interlinked-cowork && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .cursor/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/QuentinCody/interlinked-cli.git --path skills/interlinked-cowork--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install QuentinCody/interlinked-cli interlinked-cowork --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/interlinked-cowork .gemini/skills/interlinked-cowork && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .gemini/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install QuentinCody/interlinked-cli interlinked-coworkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/interlinked-cowork .github/skills/interlinked-cowork && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .github/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install QuentinCody/interlinked-cli interlinked-cowork --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QuentinCody/interlinked-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/interlinked-cowork .opencode/skills/interlinked-cowork && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "interlinked-cowork" agent skill from https://github.com/QuentinCody/interlinked-cli/tree/main/skills/interlinked-cowork into .opencode/skills/interlinked-cowork/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interlinked-cowork", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
interlinked-cowork- GitHub stars
- 178
- Token cost
- ~1.6k tokens
- SKILL.md length
- 760 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Package, test, and operate the experimental Interlinked Cowork plugin.
- Claude Desktop versus Cowork hook gaps
- SKILL.md covers Native evidence and limitations and Policy and host checks
- Needs INTERLINKED_COWORK_TOKEN
- Cowork package/capabilities/probe-prompt/report/bridge/verify/artifact
What it does
Interlinked Cowork is an agent skill from QuentinCody/interlinked-cli. Package, test, and operate the experimental Interlinked Cowork plugin. Use for Claude Desktop versus Cowork hook gaps, cowork package/capabilities/probe-prompt/report/bridge/verify/artifact, cloud versus device versus host paths, native conformance evidence, and hook runtime failures.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
The repository describes itself as: The harness for your harness. Local hooks, taste enforcement, and developer observability for AI coding agents (Claude Code, Codex, Cursor, Copilot CLI). The licence is MIT.
When your agent uses it
- Claude Desktop versus Cowork hook gaps
- Cowork package/capabilities/probe-prompt/report/bridge/verify/artifact
- Cloud versus device versus host paths
- Native conformance evidence
Example prompts
- “/interlinked-cowork”
Requirements
- A credential in INTERLINKED_COWORK_TOKEN
What it can do on your machine
Read from SKILL.md and the folder at commit a2adc8a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
INTERLINKED_COWORK_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Interlinked Cowork loads about 1.6k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 760 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from QuentinCody/interlinked-cli at commit a2adc8a, republished under its MIT licence (© QuentinCody). 760 words, ~1,641 tokens.
Download SKILL.mdSave it as
.claude/skills/interlinked-cowork/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- interlinked-cowork
- description
- Package, test, and operate the experimental Interlinked Cowork plugin. Use for Claude Desktop versus Cowork hook gaps, cowork package/capabilities/probe-prompt/report/bridge/verify/artifact, cloud versus device versus host paths, native conformance evidence, and hook runtime failures.
Interlinked Cowork
Cowork uses an uploaded plugin, separately from Claude Code settings. Ordinary Desktop Chat supports plugin skills but does not expose Cowork's hooks. Do not run enable --clients cowork; use interlinked cowork package --output <fresh-directory> and upload the resulting .plugin in Desktop Customize → Plugins. Requires the built standalone runtime, Node in the hook environment, and zip on the packaging host. After replacement, verify the displayed version/hooks and start a fresh task.
Native evidence and limitations
Run interlinked cowork capabilities --json. Dated native evidence is distinct from the current installation, which remains unmeasured until probed. On Desktop 1.49585.0 cloud mode, native deny, ask, input rewrite, and post-tool context were observed. Hook crashes and provider timeouts allowed synthetic writes. The guard launcher converts child failures, missing Node, and a 12-second internal deadline to explicit denial before the 15-second native deadline. If the provider never launches or kills the entire hook, this wrapper cannot enforce anything.
The ordinary plugin installs six lifecycle/tool hooks. A separate --probe package registers the larger Claude Code event catalog, including failure/subagent events, to measure availability; registration does not establish emission or enforcement. Keep fault injection confined to synthetic tasks, then disable the probe plugin. Do not retry denied actions through another tool.
Normal PostToolUse hooks match only Write, Edit, MultiEdit, NotebookEdit, Bash and the exact device Bash tool; reads/searches and unrelated connector tools do not trigger them. Probe subscriptions remain broad. Host guidance is encoded in PreToolUse additionalContext, including ordinary allows without a permission override; post-write artifact feedback is appended to host findings. Receipts still exclude guidance text. Pre-tool context delivery on the current native installation needs its own probe; local encoder tests are not native enforcement evidence.
interlinked cowork package --probe --output scratch/cowork-probe-1
interlinked cowork probe-prompt
interlinked cowork report events.jsonl --effects listing.txtRun the prompt through the native Cowork task UI; invoking the hook yourself is a unit test, not native evidence. Verify a clean synthetic directory first. Export evidence/events.jsonl and an independent listing containing PRESENT filename / ABSENT filename lines. Choose Download, rather than Download and open, for JSONL. The report refuses repeated campaigns and requires a positive control. Listing provenance, matching package/version/session and UI approval evidence still need review.
Receipts are metadata/hash-only with policy digest and native payload key names. They precede hook output: even an intended denial does not prove emission. They are not full transcripts, authenticated writer attribution, lossless session capture, or a substitute for effect evidence. Keep exports local unless sharing is authorized.
Show full SKILL.md (364 more words)Show less
Policy and host checks
Policy JSON: {"schema":1,"mode":"guard","deniedTools":[],"deniedPaths":[]}. Tool denials match exact native names. Paths match exact normalized native Read/Write/Edit targets, not arbitrary strings in tool content. The shared destructive-command guard handles Bash and mcp__remote-devices__device_bash. Unknown tool semantics, shell filesystem effects, browser/computer actions, connector mutations and device stage/commit remain unmeasured unless separately tested. This portable subset does not inherit repository reservations, distilled rules, supply-chain allowlists or metric baselines by itself.
Host distilled/finding rules may scope active_when.agent_source to "cowork", alone or in an array. Both runtime loaders preserve that scope; it requires the host bridge to reach the repository evaluator.
Optional bridge: { "url":"https://your-host/hook", "tokenEnv":"INTERLINKED_COWORK_TOKEN", "workspace":"project", "timeoutMs":5000 }. Credentials stay in environment variables, never in the archive. Cloud credential provisioning and public HTTPS reachability require a separate operational deployment; local loopback is not reachable from a cloud hook. The Interlinked MCP Server is a separate optional coordination service, not this bridge.
interlinked cowork bridge --workspace project --root /host/project --runtime-root /native/project --token-env INTERLINKED_COWORK_TOKEN
interlinked cowork verify /host/project
interlinked cowork artifact /path/report.xlsxThe bridge binds loopback and requires a token of at least 32 characters. It accepts only explicit Read/Write/Edit targets inside the configured workspace; realpath confinement rejects symlink escapes. Native and host snapshots must agree and remain stable during evaluation. A snapshot is not a lock, authenticated writer identity, or proof of a shared mount. Unknown routes/tools, mismatched bytes, unavailable daemon/credentials and busy checks produce no allow. Host ask decisions remain native permission requests; host input rewrites conservatively deny because host-to-native path translation is not certified. Do not expose the listener directly; use an explicitly configured authenticated HTTPS deployment if needed.
cowork verify runs tsc, biome and gitleaks and compares workspace input hashes before/after. Skipped or changed inputs remain unmeasured and exit nonzero. It does not run every quality ratchet: use interlinked-verify and interlinked-quality-gates on the actual repository for configured tests, coverage, mutation, baselines and full checks.
cowork artifact checks files up to 32 MiB: bounded Office ZIP/XML parts, cached spreadsheet error markers, heuristic placeholder text and credential patterns. Native Write post-hooks also inspect supported artifacts when bytes are accessible. XML schema/CRC validity, macro safety, formula calculation, factual/citation accuracy, visual rendering and publishing authority are outside this check. Error findings or unsupported formats exit nonzero; warnings require contextual review. See docs/cowork.md for the measured matrix and deployment gaps.
© QuentinCody, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/interlinked-cowork of QuentinCody/interlinked-cli.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit a2adc8a
Compare with similar skills
Interlinked Cowork next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Interlinked Cowork this skillQuentinCody/interlinked-cli | 178 | — | ~1.6k | Automated safety check: Pass | MIT | |
| It Operationsdavila7/claude-code-templates | 33k | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Operator Approval Loopaffaan-m/ECC | 277k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Business Operations Skillsalirezarezvani/claude-skills | 28k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Setup Coworkasgeirtj/system_prompts_leaks | 69k | — | ~3k | Automated safety check: Pass | CC0-1.0 | |
| Kubernetes Operatoralirezarezvani/claude-skills | 28k | — | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Operator Approval Loop
affaan-m/ECC
Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.
Business Operations Skills
alirezarezvani/claude-skills
A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…
Setup Cowork
asgeirtj/system_prompts_leaks
Guided Cowork setup — install a matching plugin, try a skill, connect tools.
Kubernetes Operator
alirezarezvani/claude-skills
A skill your agent uses when building a Kubernetes Operator — custom controllers that reconcile CRD state.
Experimental Design
aiming-lab/AutoResearchClaw
Best practices for designing reproducible ML experiments. An agent skill from aiming-lab/AutoResearchClaw.
More from QuentinCody/interlinked-cli
All 12 skills in this repoInterlinked
QuentinCody/interlinked-cli
Overview and router for the Interlinked CLI — a local guard, quality-enforcement, simplification-review, semantic-code-search, and observability layer for AI coding agents.
Interlinked Coordination
QuentinCody/interlinked-cli
Coordinate with other agents/humans via the optional Interlinked MCP Server, and use local checkpoints & file reservations.
Interlinked Observability
QuentinCody/interlinked-cli
Investigate agent activity and JSONL/gzip evidence. An agent skill from QuentinCody/interlinked-cli.
Interlinked Semantic Index
QuentinCody/interlinked-cli
Install and operate Interlinked's optional local semantic function index.
Interlinked Spec Audit
QuentinCody/interlinked-cli
Keep prose specs and design docs honest against the code using Interlinked's spec-audit system.
Interlinked Supply Chain
QuentinCody/interlinked-cli
Respond to blocked package installs and manage the Interlinked supply-chain allowlist.
Questions about Interlinked Cowork
What does Interlinked Cowork do?
Package, test, and operate the experimental Interlinked Cowork plugin. Interlinked Cowork is an agent skill from QuentinCody/interlinked-cli. Package, test, and operate the experimental Interlinked Cowork plugin.
When should I use Interlinked Cowork?
Interlinked Cowork fits situations like: Claude Desktop versus Cowork hook gaps; cowork package/capabilities/probe-prompt/report/bridge/verify/artifact; cloud versus device versus host paths; native conformance evidence.
How do I install Interlinked Cowork in Claude Code?
Run `npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a claude-code`. Or copy the skill folder (skills/interlinked-cowork in QuentinCody/interlinked-cli) into .claude/skills/interlinked-cowork in your project. Claude Code loads it when a task matches its description.
How do I install Interlinked Cowork in Codex?
Run `npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a codex`. Or copy the skill folder (skills/interlinked-cowork in QuentinCody/interlinked-cli) into .agents/skills/interlinked-cowork in your project. Codex loads it when a task matches its description.
Can I use Interlinked Cowork in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QuentinCody/interlinked-cli --skill interlinked-cowork -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interlinked-cowork, .gemini/skills/interlinked-cowork, .github/skills/interlinked-cowork and .opencode/skills/interlinked-cowork in your project.
What does Interlinked Cowork need to run?
Going by SKILL.md and its folder, Interlinked Cowork needs credentials named INTERLINKED_COWORK_TOKEN. Our summary lists: A credential in INTERLINKED_COWORK_TOKEN.
Does Interlinked Cowork access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Interlinked Cowork safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Interlinked Cowork use?
Interlinked Cowork is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Interlinked Cowork use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Interlinked Cowork?
Skills that share tags, products or a category with Interlinked Cowork: It Operations (davila7/claude-code-templates, 33k stars), Operator Approval Loop (affaan-m/ECC, 277k stars), Business Operations Skills (alirezarezvani/claude-skills, 28k stars) and Setup Cowork (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Interlinked Cowork?
QuentinCody (a GitHub user) maintains it in QuentinCody/interlinked-cli, which has 178 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.
Source: QuentinCody/interlinked-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.