workspace-audit

workspace-audit is a skill for Claude Code from First-Touch-Inc/firsttouch-agent-skill-packs. It costs 76 tokens per session (1,925 once invoked), scanned A, original, MIT.

A pre-launch check for a FirstTouch and HubSpot outreach workspace, covering connections, account health, ownership, logging, safety limits, and data quality.

In plain words
What is it for?
Use it when onboarding a customer, preparing a campaign, or investigating weak outreach results to produce a prioritized readiness scorecard.
Why use it?
It finds setup gaps before an outreach campaign sends messages, reducing the risk of poor coverage, unhealthy accounts, missing records, or unsafe limits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the revops-pack plugin — 2 skills shipped together

Good fit Use it when onboarding a customer, preparing a campaign, or investigating weak outreach results to produce a prioritized readiness scorecard.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit
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.

Any agent
npx skills add First-Touch-Inc/firsttouch-agent-skill-packs --skill workspace-audit
Clone the repo
git clone --depth 1 https://github.com/First-Touch-Inc/firsttouch-agent-skill-packs

Made for: Claude Code.

Or install revops-pack, the plugin that ships this one along with the rest of its 2 skills.

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 workspace-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit/github.svg)](https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit)
Your own site
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit/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 workspace-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/workspace-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00076 $0.01925
Opus 5 $0.00038 $0.00962
Sonnet 5 $0.00015 $0.00385
Haiku 4.5 $0.00008 $0.00193

Measured 9d ago against content hash 446bb11f05f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workspace-audit 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 9d 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.

plugins/revops-pack/skills/workspace-audit/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Audit

Outcome: An optional pre-flight check for teams that want to verify their setup before scaling - catch configuration gaps before they waste sends. Produce a readiness scorecard so a customer knows exactly what to fix before going live.

First-run onboarding gate

Before running this skill for the first time in a workspace, load ../../references/onboarding.md and complete the onboarding questions. Do not proceed until you know: LinkedIn account type (free/basic = no connection notes; recommend 10 connection requests/day and never exceed the FirstTouch max of 20/day; Sales Navigator/Premium = connection notes available; recommend 20 connection requests/day and never exceed the FirstTouch max of 30/day), HubSpot access (MCP, service key/private app token, HubSpot list only, or none), and which play the user wants to run. Recommend high-intent plays before outbound to keep the LinkedIn account healthy. If HubSpot is unavailable, do not run HubSpot-specific steps unless the user provides a HubSpot list FirstTouch can access.

When to use

  • New customer onboarding ("are we ready to launch?")
  • Before a big campaign push
  • Outreach is underperforming and you suspect configuration, not copy
  • Quarterly health check

Step-by-step

Every check below is one of two kinds, and the scorecard must keep them separate so a "ready" score can never hide unverified areas:

  • [AUTO] - verifiable through the connected MCPs. Mark ✅/❌ from live data only.
  • [MANUAL] - needs the user or the FirstTouch/HubSpot dashboard. Mark manual check required; never guess, and never count an unchecked item toward the readiness score.

1. Check MCP connectivity [AUTO]

  • FirstTouch MCP reachable + returns campaign/seat data? ✅/❌
  • HubSpot MCP reachable + returns contacts/owners? ✅/❌ (if a play needs it)
  • FirstTouch enrichment available and credits understood for AI SDR? ✅/❌/n/a; external Clay/Surfe enrichment MCP is optional, not required

2. LinkedIn account health (FirstTouch) [AUTO + MANUAL]

  • Seat connected and authenticated? ✅/❌
  • Current usage vs. daily limits (connection requests, messages, views) when available from FirstTouch
  • Seat status in FirstTouch Social settings: Available = good; cooldown = hit its daily limit (normal, plan volume accordingly); Action required / Disconnected / Restricted = resolve before that seat sends
  • SSI / account age / warmup status - manual/dashboard check unless FirstTouch exposes it directly
  • If FirstTouch cannot return a metric, ask the user to check the FirstTouch dashboard and mark that metric manual check required

Read the full file on GitHub · 123 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. 9d ago First seen · 123 lines · 76 tokens per session scan A 446bb11f05f2

Subscribe to this mod's changes

workspace-audit is a skill published in the GitHub repository First-Touch-Inc/firsttouch-agent-skill-packs (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,925 once invoked, about $0.0004 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.