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 instructions/dkm0315/frappe-agent/agents-mdgit 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/instructions/dkm0315/frappe-agent/agents-md)<a href="https://agentmods.dev/instructions/dkm0315/frappe-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/dkm0315/frappe-agent/agents-md.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 | $0.00577 | $0.00577 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
frappe-agent AGENTS.md 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frappe Agent Instructions
Use this repository when the task touches Frappe Framework, ERPNext, Bench, or Frappe ecosystem apps such as Helpdesk, CRM, LMS, Gameplan, Drive, HRMS, Insights, Builder, or Payments.
Core Behavior
- Inspect the bench, site, app, and repo context before proposing commands.
- Prefer the narrowest valid Frappe customization layer.
- Treat
Custom Field,Property Setter,Client Script,Server Script,Workspace,Web Page,Report, andDashboardas first-class options before invasive code changes. - Prefer Frappe-native APIs and ORM patterns before raw SQL.
- Treat raw SQL and
get_allas deliberate choices that need explanation. - Separate frontend choices into desk-native,
www, Vue/frappe-ui, React, or external SPA. - When creating DocTypes, design the form UX deliberately with useful tabs, sections, and columns; include only fields that serve the actual use case.
- Route app-specific work through the matching ecosystem model: ERPNext, Helpdesk, CRM, LMS, Gameplan, Drive, HRMS, Insights, Builder, or Payments.
Bench Guidance
- Check
sites/apps.txt,sites/common_site_config.json, installed apps, target site, and process state before mutating anything. - Do not restart an already running bench without a reason.
- Call out risky bench flags and risky app/version operations explicitly.
App Provenance
- Treat apps whose git remote is not an official Frappe remote as custom or custom-derived.
- Prefer layering changes in a custom app instead of patching upstream-derived apps directly.
ERPNext Guidance
- First determine whether a request belongs in configuration, workflow, metadata, reporting, dashboards, workspace setup, or code.
- Be broad on ERPNext module awareness, but explicit about confidence and source grounding.
Ecosystem App Guidance
- For Helpdesk, prioritize ticket lifecycle, SLA, assignment, portal, and support reporting.
- For CRM, separate leads, deals, contacts, organizations, activities, and ERPNext Selling handoff.
- For LMS, protect enrollment, learner progress, assessments, grading, and certificates.
- For Gameplan, preserve async discussion, decision, task, and workspace history.
- For Drive, protect file permissions, sharing state, storage paths, previews, and linked records.
- For HRMS, be careful with payroll, attendance, leave, claims, salary, and personal data.
- For Insights, define metric grain, filters, permissions, freshness, and dashboard decision paths.
- For Builder, optimize page UX, web forms, routing, SEO metadata, and content ownership.
- For Payments, protect secrets, verify webhooks where possible, and keep payment/accounting flows idempotent.
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 · 43 lines · 577 tokens per session scan A 7e3299c0389b
frappe-agent AGENTS.md is an instructions file published in the GitHub repository Dkm0315/frappe-agent (23 stars, last pushed 6d ago), licensed MIT. It adds 577 tokens to every session, about $0.0029 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 instructions, from other repositories
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
dev-flow AGENTS.md
AGENTS.md instructions for Innocent-children/dev-flow, covering dev flow repository instructions, authority, requirement scope, architecture and current design and product feature proposals.
codexhub AGENTS.md
Instructions for zpf2234/codexhub, covering codexhub contributor guide and project expectations.
grimoire AGENTS.md
Instructions for hon454/grimoire, covering grimoire agent protocol, repository intent, working rules, pull requests and maintenance policy.
Codex-Engineering-Workflow-Pack AGENTS.md
AGENTS.md instructions for SetraTheXX/Codex-Engineering-Workflow-Pack, a project described as: Local-first engineering workflow toolkit for Codex: skills, Coordinator Mode, worktree isolation, guarded dispatch, and parallel agent workflows.
agent-skills CLAUDE.md
Claude Code instructions for motherduckdb/agent-skills, covering motherduck skills -- claude code context, what motherduck is, default routing, install notes and non-negotiable rules.