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.
npx skills add charlieviettq/awesome-agent-skill --skill cs-sopgit clone --depth 1 https://github.com/charlieviettq/awesome-agent-skillWrote 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/charlieviettq/awesome-agent-skill/cs-sop)<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/cs-sop"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/cs-sop/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.
<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/cs-sop"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/cs-sop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.01235 |
| Opus 5 | $0.00047 | $0.00617 |
| Sonnet 5 | $0.00019 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
"cs-sop" 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.
This is a copy
95% identical to cs-sop — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Service SOP
Framework
IRON LAW: Tier the Support, Not the Customer
Every customer deserves quality service. But not every issue needs a
senior specialist. Route by ISSUE COMPLEXITY, not by customer "importance."
L1 handles 70-80% of volume (simple, repeatable)
L2 handles 15-20% (requires expertise)
L3 handles 5% (requires engineering or management)
Three-Tier Support Model
| Tier | Handles | Skills Required | Resolution Target |
|---|---|---|---|
| L1 (Basic) | FAQ, order status, password reset, simple returns | Script-following, product basics, empathy | < 5 minutes, first-contact resolution |
| L2 (Specialist) | Technical issues, billing disputes, complex returns, product defects | Deep product knowledge, judgment, negotiation | < 24 hours |
| L3 (Expert) | System bugs, legal/compliance, executive escalations, crisis | Engineering, legal, or management involvement | < 72 hours, case-by-case |
Case Categorization
| Category | Examples | Priority | SLA (First Response) |
|---|---|---|---|
| Critical | Service outage, security breach, safety issue | P1 | < 15 minutes |
| High | Payment failure, account locked, order error | P2 | < 1 hour |
| Medium | Product question, feature request, general complaint | P3 | < 4 hours |
| Low | Feedback, suggestion, general inquiry | P4 | < 24 hours |
Complaint Handling: LAST Framework
- Listen: Let the customer express fully without interrupting
- Apologize: Acknowledge their frustration sincerely ("I'm sorry this happened")
- Solve: Offer a concrete solution or next step
- Thank: Thank them for bringing it to your attention
Escalation Rules
| Trigger | Escalate To | Timeline |
|---|---|---|
| L1 can't resolve in 15 min | L2 | Immediate warm handoff |
| Customer requests supervisor | L2 or Team Lead | Within 5 minutes |
| Issue involves refund > NT$X | L2 (approval authority) | Same interaction |
| Legal threat or media mention | L3 + Legal + PR | Immediate |
| Repeat contact (3+ on same issue) | L2 + investigation | After 3rd contact |
What ships with it
1 file 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.
- 9d ago First seen · 119 lines · 94 tokens per session scan A 5beb0cf7df67
"cs-sop" is a skill published in the GitHub repository charlieviettq/awesome-agent-skill (26 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,235 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to cs-sop, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
punch-list-manager
Digital punch list management for construction project closeout. Track deficiencies, assign corrections, photo documentation, and completion verification.
safety-inspection
Digital safety inspection system for construction sites. Checklists, hazard tracking, incident reporting, and compliance documentation.
data-evolution-analysis
Analyze data evolution patterns in construction organizations. Assess digital maturity and data strategy for construction companies.
data-silo-detection
Detect and map data silos in construction organizations. Identify disconnected data sources and integration opportunities.