Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Lifecycle-Innovations-Limited/claude-ops/plugin install opsWrote 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.
[](https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/ops-rules)<a href="https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/ops-rules"><img src="https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/ops-rules.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.05234 |
| Opus 5 | $0.00014 | $0.02617 |
| Sonnet 5 | $0.00006 | $0.01047 |
| Haiku 4.5 | $0.00003 | $0.00523 |
Grade A, and why
ops-rules scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. **Subagents are not an escape hatch.** When spawning an `Agent` with access to send-tools (`mcp__gog__gmail_send`, `mcp__whatsapp__send_message`, Bash with `gog` / `curl resend.com` / etc), the subagent's prompt MUST How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ops:ops-rules
Standing rules for every ops skill. They override conflicting instructions in individual SKILL.md files.
Load this skill before acting on any /ops:* command. Details: references/cli.md (gog syntax), references/internals.md (deploy-fix fleet, credit-pool gate). Hermes primitive map: hermes-plugin/RUNTIME.md.
Rule 0 — PUBLIC REPO: No personal data ever
This is a public open-source plugin. Every file in this repo is visible to anyone on the internet.
NEVER commit:
- Real names, emails, phone numbers, or usernames (use "owner", "[email protected]", "+1234567890")
- Real store URLs, project names, or org names (use "yourstore.myshopify.com", "my-project")
- API keys, tokens, secrets, session strings, or chat IDs (use
<YOUR_TOKEN>,$ENV_VAR) - Real GitHub org names or repo slugs in examples (use "your-org/your-repo")
- Hardcoded paths like
/Users/username/...(use~or$HOME)
All user-specific data belongs in:
$PREFS_PATH(preferences.json in plugin data dir — never committed)scripts/registry.json(gitignored)$HOME/.config/claude-ops/for anything machine-scoped (e.g. the PII denylist)- Environment variables or a secrets manager
Never write preferences into the repo tree. A skill or script that writes
preferences.json, registry.json, or any prefs-shaped file next to its own
source will commit the operator's identity on the next git add -A. Resolve the
path from $PREFS_PATH or $HOME, never from $PLUGIN_ROOT/$REPO_ROOT.
This is enforced, not merely documented. tests/test-no-secrets.sh fails the
build when a prefs-shaped file is tracked in the git index (.gitignore does not
help once a file is already tracked, and git add -f bypasses it), and when a
write target resolves into the repo tree. Run it before every commit.
Enable the operator identity denylist. The scanner cannot hardcode your own
names, brands, or hostnames — that list would itself be the leak. Put one term
per line in $HOME/.config/claude-ops/pii-denylist.txt (or .pii-denylist,
gitignored) and the scanner will fail the build if any of them reach the repo.
Until you configure it, that check passes while verifying nothing.
What ships with it
2 files 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.
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.
- 4d ago First seen · 322 lines · 28 tokens per session scan A a8b3bf2d8403
ops-rules is a skill published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (186 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 5,234 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
abm-campaign-builder
Builds targeted Account-Based Marketing campaigns by identifying ideal customer profiles, mapping buying committees, creating personalized outreach sequences, and designing multi-channel engagement strategies. Use when targeting enterprise accounts, building sales playbooks, or designing vertical market penetration…
business-roi-analyzer
Calculates ROI, payback period, and financial projections for business investments including technology purchases, automation projects, hiring decisions, and equipment acquisitions. Use when evaluating whether a business investment is worth making, comparing multiple investment options, or building a business case for…
change-management-planner
Plans organizational change initiatives including technology rollouts, process redesigns, and team restructuring. Maps stakeholders, identifies resistance, designs communication plans, and builds adoption strategies with measurable milestones.
client-discovery-interview
Conducts structured discovery interviews for consultants, agencies, and service providers. Guides conversation through problem identification, stakeholder mapping, success criteria definition, budget/timeline scoping, and produces a formatted discovery brief with next steps.
cognify-workflow-analysis
Analyzes business workflows to identify automation opportunities, calculate ROI, and generate structured redesign recommendations. Use when a user describes operational pain points, wants to reduce manual work, improve team communication, automate repetitive tasks, or evaluate where AI can save time and money.
competitive-intelligence
Conducts structured competitive analysis including market positioning, feature comparison, pricing intelligence, SWOT analysis, and strategic recommendations. Use when evaluating competitors, preparing for a sales battle card, planning market entry, differentiating a product, or building a competitive strategy.