Codex-Workspace: Skill for Claude Code

.agents/skills/ssh-keychain-access/SKILL.md

ssh-keychain-access is a skill for Claude Code, Codex from RichardGeorgeDavis/Codex-Workspace. It costs 43 tokens per session (805 once invoked), scanned B, original, MIT.

A guide for recovering or setting up SSH access on macOS using passwords and private keys stored in Apple Keychain. SSH is a secure way to connect to another computer from a terminal.

In plain words
What is it for?
Use it to load SSH keys into Keychain, test public-key login, bootstrap access with a stored password, or repair authorised keys during access recovery.
Why use it?
It helps restore server access without exposing passwords or private keys in command history or tool output. It also favours key-based login over repeated password use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is RichardGeorgeDavis/Codex-Workspace's own configuration. It tells Claude Code and Codex how to work on Codex-Workspace 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 Codex-Workspace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RichardGeorgeDavis/Codex-Workspace. 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/RichardGeorgeDavis/Codex-Workspace/main/.agents/skills/ssh-keychain-access/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RichardGeorgeDavis/Codex-Workspace

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.

agentmods badge for ssh-keychain-access

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardgeorgedavis/codex-workspace/ssh-keychain-access.svg)](https://agentmods.dev/skills/richardgeorgedavis/codex-workspace/ssh-keychain-access)
Your own site
<a href="https://agentmods.dev/skills/richardgeorgedavis/codex-workspace/ssh-keychain-access"><img src="https://agentmods.dev/badge/skills/richardgeorgedavis/codex-workspace/ssh-keychain-access.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00043 $0.00805
Opus 5 $0.00022 $0.00402
Sonnet 5 $0.00009 $0.00161
Haiku 4.5 $0.00004 $0.00081

Measured 8d ago against content hash 2c3365da283b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

ssh-keychain-access scanned grade B 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ssh-keychain-login.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 /path/to/private_key
.agents/skills/ssh-keychain-access/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SSH Keychain Access

Use this skill for SSH access recovery where credentials are in macOS Keychain.

Security stance

  • Prefer SSH keys loaded with ssh-add --apple-use-keychain.
  • Use a Keychain-stored password only as an emergency fallback or to bootstrap key-based access.
  • Never print passwords, private keys, API keys, WHM credentials, or licence credentials.
  • Do not run security find-generic-password -w ... as a standalone command that would expose the password in tool output.
  • Do not use sshpass -p, put passwords in command history, or disable host key checking.
  • For root SSH, narrow the target to the specific host/IP and remove temporary access when recovery is complete.

Key-first workflow

  1. Check loaded identities:

    ssh-add -l
    
  2. Add the private key to the macOS keychain:

    chmod 600 /path/to/private_key
    ssh-add --apple-use-keychain /path/to/private_key
    
  3. Test SSH with public-key auth:

    ssh -o PreferredAuthentications=publickey user@host
    

Store a password in Keychain

Run this only in the user's local terminal. It avoids placing the password in shell history:

SERVICE="example-server-ssh"
ACCOUNT="admin@example-host"
printf 'Password for %s: ' "$ACCOUNT"
OLD_STTY=$(stty -g)
trap 'stty "$OLD_STTY"; unset SSH_PASSWORD' INT TERM EXIT
stty -echo
IFS= read -r SSH_PASSWORD
stty "$OLD_STTY"
printf '\n'
security add-generic-password -U -a "$ACCOUNT" -s "$SERVICE" -w "$SSH_PASSWORD"
unset SSH_PASSWORD
trap - INT TERM EXIT

Verify the item exists without printing the password:

security find-generic-password -a "$ACCOUNT" -s "$SERVICE"

Use the helper

Use the bundled helper when password SSH is required and the password must come from Keychain without appearing in output:

shared/skills/ssh-keychain-access/scripts/ssh-keychain-login.sh \
  --host example-host \
  --user admin \
  --service example-server-ssh \
  --account admin@example-host

Read the full file on GitHub · 105 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. 8d ago First seen · 105 lines · 43 tokens per session scan B 2c3365da283b

Subscribe to this mod's changes

ssh-keychain-access is a skill published in the GitHub repository RichardGeorgeDavis/Codex-Workspace (2 stars, last pushed 28d ago), licensed MIT. It adds 43 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

docker-compose-local-setup

Creates or updates local multi-service orchestration using docker compose. Covers compose.yaml design, service health checks, dependson readiness, env files, named volumes, migrations/seeds jobs, verification commands, and cleanup workflows for local development.

soulcodex/agentic · 52 tokens

claude-local-bridge

Access local repos from Claude on your phone via approval-gated MCP bridge.

suhteevah/claude-local-bridge · 5 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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