Agent skill · Audited from source
Ops Competitors
skill · Lifecycle-Innovations-Limited/claude-opsMIT licenceAudited 22 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 "competitor intel", "what did they...
Cite
Cite this page
ModelsAtlas. “Ops Competitors (Lifecycle-Innovations-Limited/claude-ops)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/lifecycle-innovations-limited/ops-competitors
Trust audit
Audit 0.4.1 · source read 22 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 · 22 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-competitorsThe 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 1 day 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 "competitor intel", "what did they...
---
name: ops-competitors
description: "OPS on-demand: This skill should be used when the user asks to \"competitor intel\", \"what did they..."
argument-hint: '[brand-name|refresh [brand]|add-url <brand> <competitor> <kind> <url>|alerts|help]'
allowed-tools:
- Bash
- Read
- Edit
- AskUserQuestion
effort: low
maxTurns: 15
disallowedTools:
- Write
- NotebookEdit
---
## Runtime Context
Before rendering, load competitor context:
```bash
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname $(which ops-competitors 2>/dev/null) 2>/dev/null)/..}"
OPS_DATA_DIR="${OPS_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}"
source "$PLUGIN_ROOT/scripts/lib/competitor/context.sh" 2>/dev/null || true
CTX=$(competitor_context 2>/dev/null || echo '{"configured":false,"reason":"lib_not_found"}')
```
# OPS ► COMPETITORS — Intel Dashboard
Load `ops-rules` before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If `AskUserQuestion` / `Workflow` are missing, follow Rule 10 in `ops-rules` (Hermes: numbered options / two-turn Telegram card; `delegate_task`).
Parse `$ARGUMENTS` and dispatch to the matching mode below.
---
## Mode: No args — Dashboard
Show all tracked brands with last_run, alert counts, and recent activity. Use `competitor_briefing_line` for each brand row.
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OPS ► COMPETITORS — [date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
TRACKED BRANDS ([n] total)
[brand] last run [date] [n] alerts · [n] med · [n] low
...
PENDING QUEUES
immediate: [n] daily: [n]
RECENT HIGH ALERTS (last 7d)
[timestamp] [brand] [competitor] [snippet...]
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```
If `configured == false`: print setup hint and stop.
```bash
# Load context
source "$PLUGIN_ROOT/scripts/lib/competitor/context.sh"
competitor_context --window-days 7
competitor_briefing_line
```
Mobile mode (Rule 7): one line per brand, no banner, no box-drawing.
---
## Mode: `<brand-name>` — Drill-down
Full event timeline (last 30d), top competitors, latest report, per-competitor signal breakdown.
1. Run `competitor_context --brand "<brand>" --window-days 30`
2. Print brand metadata: category, competitor list, last_run, last_discovery
3. Print per-competitor signal breakdown (group events by `.competitor`)
4. Read latest report:
```bash
SLUG=$(echo "<brand>" | tr '[:upper:] /' '[:lower:]--' | tr -cd 'a-z0-9-_.')
REPORT="$OPS_DATA_DIR/reports/competitor-intel/latest-${SLUG}.md"
[[ -f "$REPORT" ]] && head -80 "$REPORT"
```
5. Print full high-severity event timeline sorted newest-first
Output format:
```
BRAND: [name] category: [cat] last run: [date]
competitors: [a, b, c, ...]
SIGNAL BREAKDOWN
[competitor] high: [n] med: [n] low: [n]
LATEST REPORT (excerpt)
[first 80 lines of report]
EVENT TIMELINE (30d — [n] total)
[timestamp] HIGH [competitor] [source] [snippet...]
...
```
---
## Mode: `refresh [brand]`
Manually triggers the weekly intel cron immediately.
```bash
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-...}"
CRON_SCRIPT="$PLUGIN_ROOT/scripts/ops-cron-competitor-intel.sh"
# If a specific brand is given, pass it via env override
if [[ -n "$BRAND_ARG" ]]; then
BRAND_NAME="$BRAND_ARG" bash "$CRON_SCRIPT"
else
bash "$CRON_SCRIPT"
fi
```
Stream output. Inform the user when done and show updated `competitor_briefing_line`.
---
## Mode: `add-url <brand> <competitor> <kind> <url>`
Add a page-diff monitored URL to `preferences.json`. Valid `<kind>` values: `pricing`, `features`, `changelog`, `careers`.
1. Validate args — if any missing, explain usage and stop.
2. Show the proposed change:
```
Add URL for [brand] → [competitor] ([kind]):
[url]
```
3. AskUserQuestion: `[Add]` / `[Cancel]`
4. On confirm, merge via jq:
```bash
PREFS="$OPS_DATA_DIR/preferences.json"
jq --arg brand "$BRAND" --arg comp "$COMP" --arg kind "$KIND" --arg url "$URL" '
.competitor_intel.urls[$brand][$comp][$kind] = $url
' "$PREFS" > /tmp/prefs-tmp.json && mv /tmp/prefs-tmp.json "$PREFS"
```
5. Confirm written.
---
## Mode: `alerts`
Tail the last 20 lines of the alerts log:
```bash
ALERTS="$OPS_DATA_DIR/reports/competitor-intel/alerts.log"
if [[ -f "$ALERTS" ]]; then
tail -20 "$ALERTS"
else
echo "No alerts log found at $ALERTS"
fi
```
---
## Mode: `help` / unknown args
Print available subcommands:
```
ops-competitors — dashboard (all brands)
ops-competitors <brand> — drill-down: events, report, breakdown
ops-competitors refresh [brand] — run intel cron now (optional brand filter)
ops-competitors add-url <b> <c> <k> <url> — add page-diff URL to preferences.json
ops-competitors alerts — tail alerts.log (last 20 lines)
ops-competitors help — this message
```
---
## Error states
- `configured == false` → print `"Competitor-intel not configured. Run /ops:setup competitor-intel to get started."` and stop.
- `CRON_SCRIPT` not found → print path and stop.
- `PREFS` not writable for `add-url` → surface error, do not silently fail.Excerpt, first 5,193 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
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
- ✓SAFE B 89 / 100
first audit · source
90a91797a66f
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 "which keys are set", "missing...
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...
Questions about Ops Competitors
What does the Ops Competitors skill do?
Is Ops Competitors safe to install?
What can Ops Competitors access on my machine?
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 · 22 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 Competitors skill do?
- Is Ops Competitors safe to install?
- What can Ops Competitors access on my machine?