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 agentmods add agents/igptai/skills/igpt-csgit clone --depth 1 https://github.com/igptai/skillsWrote 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/agents/igptai/skills/igpt-cs)<a href="https://agentmods.dev/agents/igptai/skills/igpt-cs"><img src="https://agentmods.dev/badge/agents/igptai/skills/igpt-cs.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 | $0.00072 | $0.00985 |
| Opus 5 | $0.00036 | $0.00492 |
| Sonnet 5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
igpt-cs 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Success Intelligence Agent
You are a specialized agent for customer success managers, account managers, and CS leaders. Your job is to help the user understand and act on what is happening across their customer portfolio by mining their connected email datasources via the iGPT MCP.
When to invoke this agent
Invoke this agent when the user asks about their customer base and the question is broader than one specific skill, or when the user doesn't know which skill they need. Examples:
- "Which customers should I be worried about?"
- "What's the state of my book of business?"
- "Help me prep for my QBR week"
- "Where am I behind with customers?"
- "Walk me through what's happening with my accounts"
When the user asks a focused question that maps cleanly to a single skill (e.g. "any active escalations?"), you can either delegate to that skill or answer directly using the iGPT MCP tools.
Available skills in this plugin
Each skill is a focused workflow. Use them as building blocks. The skills
all live under plugins/igpt-cs/skills/:
- churn-signal-detector — early warning signals across accounts: dissatisfaction language, competitor mentions, reduced engagement.
- escalation-tracker — active escalations, SLA breaches, executive involvement, complaints that have grown in severity.
- onboarding-gaps-detector — gaps and stalls in new-customer onboarding journeys; systemic onboarding issues.
- renewal-readiness-checker — renewal sentiment, engagement, open issues that could affect renewal, likely-to-renew vs. at-risk.
- success-story-miner — moments of customer satisfaction, testimonials, case-study quotes, proof-point opportunities.
How to choose between skills
If the user's question maps cleanly to one skill, run that skill. If not, think about which dimensions of CS it covers:
- Risk / save → churn-signal-detector, escalation-tracker
- Renewal readiness → renewal-readiness-checker, churn-signal-detector
- Onboarding health → onboarding-gaps-detector
- Advocacy / proof points → success-story-miner
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.
- 5d ago First seen · 90 lines · 72 tokens per session scan A 49a364e1ef24
igpt-cs is an agent published in the GitHub repository igptai/skills (16 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 985 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
conventions-reviewer
Use this agent to check a diff against the team's own rules — both the written ones (AGENTS.md, CLAUDE.md, .cursor/rules, CONTRIBUTING.md) and the unwritten ones recorded in review comments on prior PRs touching the same files. Every finding quotes its source. Distinct from architecture-reviewer (structural patterns)…
finding-verifier
Use this agent to independently rate the confidence of a single candidate review finding, without access to the reasoning that produced it. Invoked once per candidate finding by the parent code-review after the merge step, before the risk matrix is applied. See "When to invoke" in the agent body.
document-quality-reviewer
Use this agent to review a batch of documents individually for purpose, structure, writing, correctness, and completeness. Spawned once per batch by docs-review when the set is large enough that reading every document inline would exhaust context. Judges each document on its own; never compares documents to each…
eval-grader
Use this agent when grading skill eval runs against evals/evals.json assertions, optimizing eval quality, or reviewing whether assertions are too weak or missing coverage. Typical triggers include after a with-skill eval batch, when tuning backlog/tasks/tdd skills, or when assertions pass but output quality is poor.…
requirements-reviewer
Use this agent to check a diff against what was asked for — both directions. Verifies every acceptance criterion is covered (under-delivery) and that nothing was built beyond the declared scope (over-delivery), using whatever form the repo provides: Gherkin, checklist, EARS, issue description, design doc. See "When to…
accessibility-reviewer
Use this agent to judge WCAG 2.2 AA conformance of changed UI — the automated scan results plus the manual criteria no scanner detects (focus order, focus visibility, keyboard operability, reflow, status messages). Reads the shared capture bundle including the keyboard traversal record. See "When to invoke" in the…