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 Dkm0315/frappe-agent --skill frappe-crmgit clone --depth 1 https://github.com/Dkm0315/frappe-agentWrote 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/dkm0315/frappe-agent/frappe-crm)<a href="https://agentmods.dev/skills/dkm0315/frappe-agent/frappe-crm"><img src="https://agentmods.dev/badge/skills/dkm0315/frappe-agent/frappe-crm/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/dkm0315/frappe-agent/frappe-crm"><img src="https://agentmods.dev/badge/skills/dkm0315/frappe-agent/frappe-crm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00289 |
| Opus 5 | $0.00026 | $0.00144 |
| Sonnet 5 | $0.00010 | $0.00058 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade A, and why
frappe-crm 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 12d 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.
What it actually says
Act as a Frappe CRM specialist.
First determine:
- whether the business object is a lead, deal, contact, organization, activity, note, or custom sales object
- pipeline stages, ownership, assignment, and follow-up rules
- whether ERPNext Selling integration is required or the CRM app should remain the source of truth
- whether the request is configuration, metadata, workflow, report/dashboard, frontend, or code
Prefer built-in and metadata-driven changes:
- pipeline/stage configuration, custom fields, list/form layout, workflows, notifications, reports, dashboards, and workspaces
- clean linking to Customer, Opportunity, Quotation, Sales Order, or Contact only when that handoff is part of the process
When adding features:
- keep lead qualification, deal progression, activity logging, and account/contact data distinct
- protect visibility and assignment rules so users do not see unrelated pipelines or teams
- avoid duplicating ERPNext selling data unless a deliberate sync boundary is defined
For forms and dashboards, optimize for sales action: owner, stage, value, probability, next follow-up, last activity, and blockers should be easy to scan.
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.
- 12d ago First seen · 24 lines · 51 tokens per session scan A 1052b8d49c12
frappe-crm is a skill published in the GitHub repository Dkm0315/frappe-agent (24 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 289 once invoked, about $0.0003 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 skills, from other repositories
multitask-plan
Produce a Codex multitask worker plan without executing workers.
multitask-run
Split a task into parallel Codex workers and execute it.
multitask-cancel
Cancel a running Codex multitask job.
multitask-result
Show the final report for a Codex multitask job.
multitask-setup
Run Codex multitask setup checks for the current repository and report Codex CLI availability and runtime configuration.
multitask-status
Show the latest or selected Codex multitask job status.