Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Ops Leadgen

skill · Lifecycle-Innovations-Limited/claude-opsMIT licenceAudited 31 Oct 2026 · source 8569ddefd898

★ 547pushed today
✓SAFEGrade B · 89/100 · 31 Oct 2026 · 8569dde
547repo stars · whole Lifecycle-Innovations-Limited/claude-ops

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 8569ddefd898 and found no filesystem, network or shell access and no hard-coded secrets. What it does: OPS on-demand: This skill should be used when the user asks to "leadgen drafts", "cold email approve"...

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Ops Leadgen (Lifecycle-Innovations-Limited/claude-ops)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-leadgen

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 8569ddefd898 · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherLifecycle-Innovations-Limited GitHub organizationOwner of the repository this skill is read from
  • Source folderLifecycle-Innovations-Limited/claude-ops/claude-ops/skills/ops-leadgenThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict8569ddefd898A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: OPS on-demand: This skill should be used when the user asks to "leadgen drafts", "cold email approve"...

---
name: ops-leadgen
description: "OPS on-demand: This skill should be used when the user asks to \"leadgen drafts\", \"cold email approve\"..."
argument-hint: '[review | send --draft-id N | usage | scrape | draft]'
allowed-tools:
  - Bash
  - Read
effort: low
maxTurns: 20
---

# ops-leadgen

Load `ops-rules` before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If `AskUserQuestion` / `Workflow` are missing, follow Rule 10 in `ops-rules` (Hermes: numbered options / two-turn Telegram card; `delegate_task`).

Wraps `my-project-leadgen` CLI for the daily leadgen review-and-send loop.

**Repo:** `~/Projects/my-project-b2b-leadgen`
**DB:** `~/Projects/my-project-b2b-leadgen/leads.db` (gitignored)
**Run with Doppler:** `doppler run --project my-project-b2b-leadgen --config dev -- my-project-leadgen <cmd>`

## Argument routing

| Argument             | Action                                           |
| -------------------- | ------------------------------------------------ |
| `review` (default)   | Show pending drafts one-by-one, approve or skip  |
| `send --draft-id N`  | Hand one draft to the host's approved outbound gate (Rule 6) |
| `usage`              | Print today's Apollo reveals + Apify runs        |
| `scrape [--limit N]` | Discover new NL HR contacts via Apollo           |
| `enrich`             | Run Apify enrichment on unenriched leads         |
| `draft`              | Generate Claude NL/EN drafts for undrafted leads |

## Review + send flow (Rule 6)

**NEVER send multiple drafts in one turn. Each send is a separate staged-draft → approval → send cycle.**

1. Run `my-project-leadgen review` (or fetch pending drafts from DB directly)
2. For each pending draft, show the user:
   - Lead: name, title, company, email
   - Language, subject, full body
3. Ask: `[Send]` / `[Skip]` / `[Stop review]`
4. On `[Send]`: one draft, one approval, one send, only through the host's
   approved outbound gate.
   a. Pass the exact recipient, subject and full latest body to that gate; it shows
      the complete text and binds the owner's native yes to those bytes.
   b. Approval is that native yes on the shown draft only. A typed word, file, token
      or counter is never consent, and one approval never covers another draft.
   c. After the gate reports delivery, confirm it on a fresh read of the sent mail,
      then record the send in the leadgen database.
   d. If the gate refuses or cannot send this channel, keep the draft pending with the
      exact diagnostic. Never run a direct sender as a substitute for the gate.
5. Move to the next draft only after the current one is fully resolved.

## Scrape → enrich → draft (pipeline)

```bash
# Step 1: discover contacts (costs Apollo reveals — check usage first)
doppler run --project my-project-b2b-leadgen --config dev -- \
  my-project-leadgen usage

doppler run --project my-project-b2b-leadgen --config dev -- \
  my-project-leadgen scrape --limit 50

# Step 2: enrich with Apify website crawler
doppler run --project my-project-b2b-leadgen --config dev -- \
  my-project-leadgen enrich

# Step 3: generate Claude drafts
doppler run --project my-project-b2b-leadgen --config dev -- \
  my-project-leadgen draft

# Step 4: review + send (Rule-6 gated, one at a time)
doppler run --project my-project-b2b-leadgen --config dev -- \
  my-project-leadgen review
```

## Daily usage cap

- Apollo reveals: **200/day** max (tracked in `leads.db daily_usage`)
- Apify runs: ~$0.02/run (3 pages per domain)
- Always run `usage` first to check remaining reveals before scraping

## DB queries (read-only diagnostics)

```bash
# Pending drafts count
sqlite3 ~/Projects/my-project-b2b-leadgen/leads.db \
  "SELECT count(*) FROM drafts WHERE status='pending';"

# Today's sends
sqlite3 ~/Projects/my-project-b2b-leadgen/leads.db \
  "SELECT d.subject, l.email, s.sent_at FROM sends s
   JOIN drafts d ON d.id=s.draft_id
   JOIN leads l ON l.id=d.lead_id
   WHERE date(s.sent_at)=date('now');"
```

## Rule 6 — no exceptions

Per `ops-rules` Rule 6: every outbound send is one draft, one approval, one send,
only through the host's approved outbound gate. A local file, shell token or
counter is defense in depth at most, never the owner's consent. Each draft needs its
own native approval on the latest shown text.

Excerpt, first 4,334 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 8569dde

Download folder ↗
git clone https://github.com/Lifecycle-Innovations-Limited/claude-ops
git -C claude-ops checkout 8569ddefd898

The author documents no install command, so this uses the repository directly. Our verdict covers commit 8569ddefd898 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 8569ddefd898

Questions about Ops Leadgen

What does the Ops Leadgen skill do?
Business operating system for Claude Code — 57 skills, 21 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS monitoring, revenue (Stripe+RevenueCat), e-commerce (Shopify), marketing (Klaviyo/Meta/GA4), voice (Bland/ElevenLabs), APM (Datadog/NewRelic/OT
Is Ops Leadgen safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Ops Leadgen access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (8569ddefd898), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.