covalent-bond: Skill for Claude Code

.claude/skills/covalent-bond-run/SKILL.md

covalent-bond-run is a skill for Claude Code from gopalrajsuresh/covalent-bond. It costs 77 tokens per session (1,071 once invoked), scanned A, original, MIT.

A setup and troubleshooting guide for Covalent Bond, which pairs two AI coding agents over an end-to-end-encrypted channel. It covers the MCP server, relay, sessions, file sharing, and connection problems.

In plain words
What is it for?
Use it to install and test Covalent Bond, start a local or deployed relay, register the MCP server, create or join a session, and send files.
Why use it?
It explains the pieces needed for two agents on different machines to connect and helps diagnose failed sessions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex; built for cline.

This is gopalrajsuresh/covalent-bond's own configuration. It tells Claude Code how to work on covalent-bond itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything covalent-bond configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is COVALENT_RELAY_URL=<relay> node two-machine/host.js # prints the code.

Reuse

Borrowing it

Nothing to install: this file belongs to gopalrajsuresh/covalent-bond. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gopalrajsuresh/covalent-bond/main/.claude/skills/covalent-bond-run/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gopalrajsuresh/covalent-bond

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 covalent-bond-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/gopalrajsuresh/covalent-bond/covalent-bond-run/github.svg)](https://agentmods.dev/skills/gopalrajsuresh/covalent-bond/covalent-bond-run)
Your own site
<a href="https://agentmods.dev/skills/gopalrajsuresh/covalent-bond/covalent-bond-run"><img src="https://agentmods.dev/badge/skills/gopalrajsuresh/covalent-bond/covalent-bond-run/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 covalent-bond-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/gopalrajsuresh/covalent-bond/covalent-bond-run"><img src="https://agentmods.dev/badge/skills/gopalrajsuresh/covalent-bond/covalent-bond-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,071 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00077 $0.01071
Opus 5 $0.00039 $0.00535
Sonnet 5 $0.00015 $0.00214
Haiku 4.5 $0.00008 $0.00107

Measured 11d ago against content hash 4be3784f2ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

covalent-bond-run scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `Relay health check failed` | Check `COVALENT_RELAY_URL`; `curl <relay>/health` should return `{"status":"ok",...}` |
.claude/skills/covalent-bond-run/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running Covalent Bond

Covalent Bond pairs two AI coding agents on different machines over an end-to-end-encrypted channel. This skill covers setup, pairing, and troubleshooting. It assumes Node.js v18+.

1. Install

npm install
npm test            # confirms the build works (uses an in-process mock relay)

2. Choose a relay

The two machines connect through a relay. Options:

  • Local mock relay (dev / same-network testing): npm run relay:dev starts one on http://localhost:8787. Point both sides at it with COVALENT_RELAY_URL=http://localhost:8787.
  • Deployed Cloudflare Worker (real cross-machine use): set COVALENT_RELAY_URL=https://<your-worker>.workers.dev. Deploying one is a maintainer task; see the deploy skill / cloudflare-worker/README.md.

The relay never sees plaintext, keys, or the session code.

3. Register the MCP server with the agent

Claude Code:

claude mcp add --scope user covalent -- node /absolute/path/to/covalent-bond/bin/cli.js

Other MCP clients (Cursor, Codex, Windsurf, Cline, …): add a stdio MCP server whose command is node /absolute/path/to/covalent-bond/bin/cli.js. Set COVALENT_RELAY_URL in the server's environment, or copy .env.example to .env in the covalent-bond folder (the server reads it at startup; a real environment variable takes precedence).

4. Pair two agents

The nine tools are bond_connect, bond_join, bond_send, bond_message, bond_wait, bond_accept, bond_decline, bond_status, bond_end.

  1. Machine A (host): ask the agent to "create a Covalent Bond session" → it calls bond_connect and returns a session code like AbCd-1234-XyZw.
  2. Share the code with Machine B out-of-band: chat, voice, in person. Never paste it into the relay; its secrecy is what secures the channel.
  3. Machine B (guest): "join Covalent Bond session AbCd-1234-XyZw" → it calls bond_join.
  4. Check bond_status on both until it shows Secure channel established.
  5. Send a file: "send src/auth.js to my peer"bond_send. The peer sees a consent prompt and must bond_accept before the file is written.
  6. End: "end the Covalent Bond session"bond_end.

Read the full file on GitHub · 93 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. 11d ago First seen · 93 lines · 77 tokens per session scan A 4be3784f2ca1

Subscribe to this mod's changes

covalent-bond-run is a skill published in the GitHub repository gopalrajsuresh/covalent-bond (0 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 1,071 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.