Agent skill · Audited from source
Ops Credentials
skill · Lifecycle-Innovations-Limited/claude-opsMIT licenceAudited 23 Oct 2026 · source 90a91797a66f
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 90a91797a66f 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 "which keys are set", "missing...
Cite
Cite this page
ModelsAtlas. “Ops Credentials (Lifecycle-Innovations-Limited/claude-ops)”. Retrieved 23 Oct 2026. https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-credentials
Trust audit
Audit 0.4.1 · source read 23 Oct 2026
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
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
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 90a91797a66f · 23 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-credentialsThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict90a91797a66fA new audit runs when the source changes
- Repository statusNot archivedLast push 2 days ago
- 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 "which keys are set", "missing...
---
name: ops-credentials
description: "OPS on-demand: This skill should be used when the user asks to \"which keys are set\", \"missing..."
argument-hint: '[--service <name>] [--json]'
allowed-tools:
- Bash
- Read
- AskUserQuestion
effort: low
maxTurns: 5
---
# OPS ► CREDENTIALS
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`).
## CLI/API Reference
| Command | Output |
| -------------------------------------- | ---------------------------------------------- |
| `bin/ops-credentials` | Human table — configured + missing per service |
| `bin/ops-credentials --json` | JSON array, one entry per credential |
| `bin/ops-credentials --service stripe` | Filter to one integration |
The bin script is the source of truth. It scans these sources in order and reports the FIRST hit per credential:
1. Shell env (`$STRIPE_SECRET_KEY`, etc.)
2. `$OPS_DATA_DIR/preferences.json` (`.revenue.stripe.secret_key`, etc., including `doppler:KEY` references that get resolved live)
3. macOS Keychain (`security find-generic-password -s <name> -w`)
4. Dashlane (`dcli password <keyword> --output json`)
Values shorter than 12 chars print as `•••`; longer values print as `first6•••last4`.
## Your task
When the user runs `/ops:credentials`:
1. **Run** `bin/ops-credentials` and present the output verbatim — it's already formatted for the user's terminal (compact mode for SSH/mobile, table layout otherwise).
2. **Offer follow-ups via AskUserQuestion (max 4 options per Rule 1):**
```
What would you like to do next?
[Configure a missing service — pick one to set up now]
[Re-audit a specific service]
[Export to JSON]
[Done]
```
3. **On "Configure missing"**: list missing services 4-at-a-time via `AskUserQuestion`. For each pick, call the `/ops:setup <service>` skill.
4. **On "Re-audit specific"**: ask for the service name and run `bin/ops-credentials --service <name>`.
5. **On "Export to JSON"**: run `bin/ops-credentials --json` and write the result to `/tmp/ops-credentials-audit-$(date +%s).json`. Print the path.
## Why this skill exists
Claude Code's plugin settings UI cannot introspect external credential stores. If a user has `STRIPE_SECRET_KEY` in macOS Keychain or `klaviyo_api_key` in Doppler, the settings panel shows those fields as empty (because the value isn't stored in Claude Code's user-config). The user can't tell at a glance which integrations they've already wired up.
`/ops:credentials` solves that — one command, one table, complete picture of which integrations are ready to use vs which still need `/ops:setup`.
## Homey Pro (Home Automation)
| Field | Value |
| ------------ | ----------------------------------------------------------------------------------------------------------- |
| Service name | Homey Pro |
| Category | Home Automation |
| Keys | `HOMEY_LOCAL_URL`, `HOMEY_LOCAL_TOKEN`, `HOMEY_CLOUD_TOKEN`, `HOMEY_ID` |
| Storage | `$PREFS_PATH` → `.home_automation.homey_local_url`, `.homey_local_token`, `.homey_cloud_token`, `.homey_id` |
| Required | `HOMEY_LOCAL_URL`, `HOMEY_LOCAL_TOKEN` |
| Optional | `HOMEY_CLOUD_TOKEN` (off-LAN fallback), `HOMEY_ID` (cloud API only) |
**Rotation:** Revoke the current token at `https://my.homey.app/manager/tokens`, generate a new one, then rerun `/ops:setup --section home` to save the replacement.
---
## Privacy guarantees
- **Never prints raw values.** All output is masked.
- **Never copies values to disk.** Reads happen in-process; the JSON export contains only `{service, label, configured, masked, source}`, never the raw secret.
- **Read-only.** Does not write to keychain, Doppler, or preferences.
## Mobile / SSH (Rule 7)
When `$SSH_CONNECTION` / `$SSH_CLIENT` / `$SSH_TTY` is set or `$OPS_MOBILE=1`, the bin script auto-switches to compact one-line-per-cred format. Skill output should pass it through unchanged.Excerpt, first 4,649 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 90a9179
git clone https://github.com/Lifecycle-Innovations-Limited/claude-ops git -C claude-ops checkout 90a91797a66f
The author documents no install command, so this uses the repository directly. Our verdict covers commit 90a91797a66f only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
90a91797a66f
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-credentials/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All automation skills →Lifecycle-Innovations-Limited/claude-ops
This skill should be used when the user asks to "ops command center", "/ops:ops", or "run the business". Single discovery router for all business operations — communications, projects, infrastructure, revenue,…
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "competitor intel", "what did they...
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "deploy auto-fix", "failed deploy", or...
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "control the desktop", "click on...
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "plugin broken", "ops doctor", or...
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "shopify", "orders inventory", or...
Add this badge to your README
[](https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-credentials/)
<a href="https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-credentials/"><img src="https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-credentials/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about Ops Credentials
What does the Ops Credentials skill do?
Is Ops Credentials safe to install?
What can Ops Credentials access on my machine?
Which assistants does Ops Credentials work with?
How current is this page?
Sources
- github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/cl — the audited source at commit 90a91797a66f and every finding aboveObserved · 23 Oct 2026
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.
- What does the Ops Credentials skill do?
- Is Ops Credentials safe to install?
- What can Ops Credentials access on my machine?