Configuring Horizon
coollabsio/coolify
A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.
A skill your agent uses when implementing the Frappe/ERPNext permission system.
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissions --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .claude/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .claude/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissionsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .agents/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .agents/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .cursor/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .cursor/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git --path skills/source/core/frappe-core-permissions--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .gemini/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .gemini/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissionsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .github/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .github/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Impertio-Studio/Frappe_Claude_Skill_Package frappe-core-permissions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/source/core/frappe-core-permissions .opencode/skills/frappe-core-permissions && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "frappe-core-permissions" agent skill from https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/core/frappe-core-permissions into .opencode/skills/frappe-core-permissions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frappe-core-permissions", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
frappe-core-permissionsA skill your agent uses when implementing the Frappe/ERPNext permission system.
Frappe Core Permissions is an agent skill from Impertio-Studio/Frappe_Claude_Skill_Package. Use when implementing the Frappe/ERPNext permission system. Covers roles, user permissions, perm levels, data masking, and permission hooks for v14/v15/v16. Prevents common access control mistakes and security issues. Keywords: permissions, roles, user permissions, perm levels, data masking,, restrict records, who can see what, department access, row-level, user cannot see document, access denied. access control, security, haspermission.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/anti-patterns.md`, `references/examples.md` and `references/permission-api-reference.md`). Compatibility notes: Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16.
It sits in Backend & APIs, covering Authorization and RBAC. The repository describes itself as: 60 deterministic Claude AI skills for Frappe Framework & ERPNext v14-v16 development and operations. The licence is MIT.
10 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 36cfa80. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and json).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16.
From compatibility in the SKILL.md frontmatter.
Frappe Core Permissions loads about 2.9k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 117 tokens; SKILL.md has 688 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Impertio-Studio/Frappe_Claude_Skill_Package at commit 36cfa80, republished under its MIT licence (© Impertio-Studio). 688 words, ~2,921 tokens.
.claude/skills/frappe-core-permissions/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.Deterministic patterns for the five-layer Frappe permission system.
| Layer | Controls | Configured Via | Version |
|---|---|---|---|
| Role Permissions | What users CAN do | DocType permissions table | All |
| User Permissions | WHICH records users see | User Permission DocType | All |
| Perm Levels | WHICH fields users see/edit | Field permlevel property | All |
| Permission Hooks | Custom deny logic | hooks.py | All |
| Data Masking | Masked field values | Field mask property | [v16+] |
Need to control access?
├── Who can Create/Read/Write/Delete a DocType? → Role Permissions
├── Which specific records can a user see? → User Permissions
├── Which fields should be hidden? → Perm Levels (permlevel 1+)
├── Which fields show masked values? → Data Masking [v16+]
├── Custom runtime deny logic? → has_permission hook
├── Filter list queries dynamically? → permission_query_conditions hook
└── Share one document with one user? → frappe.share
Checking permissions in code?
├── Before action → frappe.has_permission() or doc.has_permission()
├── Raise on denial → doc.check_permission() or throw=True
├── System bypass → doc.flags.ignore_permissions = True (ALWAYS document why)
└── List query → ALWAYS use frappe.get_list() for user-facing data| Type | API Check | Applies To |
|---|---|---|
read | frappe.has_permission(dt, "read") | All DocTypes |
write | frappe.has_permission(dt, "write") | All DocTypes |
create | frappe.has_permission(dt, "create") | All DocTypes |
delete | frappe.has_permission(dt, "delete") | All DocTypes |
submit | frappe.has_permission(dt, "submit") | Submittable only |
cancel | frappe.has_permission(dt, "cancel") | Submittable only |
amend | frappe.has_permission(dt, "amend") | Submittable only |
select | frappe.has_permission(dt, "select") | Link fields [v14+] |
report | N/A | Report Builder access |
export | N/A | Excel/CSV export |
import | N/A | Data Import Tool |
share | N/A | Share with other users |
print | N/A | Print/PDF generation |
email | N/A | Send email |
mask | Role permission for unmasked view | Data Masking [v16+] |
| Role | Assigned To | Notes |
|---|---|---|
Guest | Everyone (including anonymous) | Public pages |
All | All registered users | Basic authenticated access |
Administrator | Only the Administrator user | ALWAYS has all permissions |
Desk User | System Users only | [v15+] |
# DocType-level
frappe.has_permission("Sales Order", "write")
# Document-level (by name or object)
frappe.has_permission("Sales Order", "write", "SO-00001")
frappe.has_permission("Sales Order", "write", doc=doc)
# For specific user
frappe.has_permission("Sales Order", "read", user="john@example.com")
# Throw on denial
frappe.has_permission("Sales Order", "delete", throw=True)
# Debug mode — prints evaluation steps
frappe.has_permission("Sales Order", "read", debug=True)
print(frappe.local.permission_debug_log)doc = frappe.get_doc("Sales Order", "SO-00001")
# Returns bool
if doc.has_permission("write"):
doc.status = "Approved"
doc.save()
# Raises frappe.PermissionError if denied
doc.check_permission("write")from frappe.permissions import get_doc_permissions
perms = get_doc_permissions(doc)
# {'read': 1, 'write': 1, 'create': 0, 'delete': 0, ...}
perms = get_doc_permissions(doc, user="john@example.com")Restrict users to specific Link field values (e.g., specific Company, Territory).
from frappe.permissions import add_user_permission, remove_user_permission
# Restrict user to one company
add_user_permission(
doctype="Company",
name="My Company",
user="john@example.com",
is_default=1, # auto-fill in new documents
applicable_for="Sales Order" # only for this DocType (optional)
)
# Remove restriction
remove_user_permission("Company", "My Company", "john@example.com")
# Query current restrictions
from frappe.permissions import get_user_permissions
perms = get_user_permissions("john@example.com")
# {"Company": [{"doc": "My Company", "is_default": 1}], ...}Grant access to a single document for a specific user.
from frappe.share import add as add_share, remove as remove_share
add_share("Sales Order", "SO-00001", "jane@example.com",
read=1, write=1, share=0, notify=1)
remove_share("Sales Order", "SO-00001", "jane@example.com")
# Share with everyone
add_share("Sales Order", "SO-00001", everyone=1, read=1)Group fields by permlevel (0-9). Level 0 MUST be granted before higher levels.
{
"fields": [
{"fieldname": "employee_name", "permlevel": 0},
{"fieldname": "salary", "permlevel": 1}
],
"permissions": [
{"role": "Employee", "permlevel": 0, "read": 1},
{"role": "HR Manager", "permlevel": 0, "read": 1, "write": 1},
{"role": "HR Manager", "permlevel": 1, "read": 1, "write": 1}
]
}Rule: Levels do NOT imply hierarchy. Level 2 is not "higher" than level 1. They are independent field groups.
Fields with mask=1 show masked values (e.g., ****, +91-811XXXXXXX) to users without mask permission.
{
"fieldname": "phone_number", "fieldtype": "Data", "mask": 1
}Grant mask permission to roles that MUST see unmasked values:
{"role": "HR Manager", "permlevel": 0, "read": 1, "mask": 1}CRITICAL: Data masking does NOT apply to frappe.db.sql() or Query Reports with raw SQL. You MUST mask manually in custom SQL queries.
Can only deny access. NEVER returns True to grant. ALWAYS returns None to continue standard checks.
# hooks.py
has_permission = {
"Sales Order": "myapp.permissions.check_order_permission"
}# myapp/permissions.py
def check_order_permission(doc, ptype, user):
if ptype == "write" and doc.docstatus == 2:
if "Sales Manager" not in frappe.get_roles(user):
return False
return None # ALWAYS return None by defaultReturns SQL WHERE clause fragment. Only affects get_list(), NOT get_all().
# hooks.py
permission_query_conditions = {
"Customer": "myapp.permissions.customer_query"
}def customer_query(user):
if not user:
user = frappe.session.user
if "Sales Manager" in frappe.get_roles(user):
return ""
return f"`tabCustomer`.owner = {frappe.db.escape(user)}"ALWAYS use frappe.db.escape() — NEVER use string concatenation with raw user input.
| Method | User Permissions | Query Hook | Use For |
|---|---|---|---|
frappe.get_list() | Applied | Applied | User-facing queries |
frappe.get_all() | Ignored | Ignored | System/background queries |
ALWAYS use get_list() when returning data to users. get_all() bypasses ALL permission filtering.
{"role": "Sales User", "read": 1, "write": 1, "create": 1, "if_owner": 1}@frappe.whitelist()
def sensitive_action():
frappe.only_for(["Manager", "Administrator"])
# Only reaches here if user has one of these roles# On document — ALWAYS add a comment explaining the reason
doc.flags.ignore_permissions = True
doc.save()
# On method call
doc.save(ignore_permissions=True)
doc.insert(ignore_permissions=True)frappe.has_permission() — NEVER check roles directly for access controlfrappe.get_list() for user-facing queries — NEVER get_all()frappe.db.escape(user)`tabDocType`.fieldnameNone in has_permission hooks by default — NEVER Truefrappe.clear_cache()ignore_permissions usage with a commenthas_permission hooks — return False to deny| Do NOT | Do Instead |
|---|---|
if "Role" in frappe.get_roles() for access | frappe.has_permission(dt, ptype) |
frappe.get_all() for user queries | frappe.get_list() |
return True in has_permission hook | return None |
f"owner = '{user}'" in SQL | f"owner = {frappe.db.escape(user)}" |
frappe.throw() in permission hooks | return False |
frappe.db.set_value() for user-facing updates | doc.save() with permission check |
| Sensitive data in error messages | Generic frappe.PermissionError |
| Feature | v14 | v15 | v16 |
|---|---|---|---|
select permission | Yes | Yes | Yes |
Desk User role | No | Yes | Yes |
Data Masking (mask field) | No | No | Yes |
mask permission type | No | No | Yes |
| Custom Permission Types | No | No | Experimental |
False = denied)| File | Contents |
|---|---|
| permission-types-reference.md | All permission types with options |
| permission-api-reference.md | Complete API with all signatures |
| permission-hooks-reference.md | Hook patterns and examples |
| examples.md | Working implementation examples |
| anti-patterns.md | Common mistakes and fixes |
frappe-core-database — Database operations that respect permissionsfrappe-core-api — API endpoints with permission checksfrappe-syntax-controllers — Controller permission validationfrappe-syntax-hooks — Hook configuration patternsVerified against Frappe docs 2026-03-20 | Frappe v14/v15/v16
© Impertio-Studio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (references) in skills/source/core/frappe-core-permissions of Impertio-Studio/Frappe_Claude_Skill_Package.
Open the folder on GitHubat commit 36cfa80
Frappe Core Permissions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Frappe Core Permissions this skillImpertio-Studio/Frappe_Claude_Skill_Package | 189 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Configuring Horizoncoollabsio/coolify | 63k | 4 repos | ~898 | Automated safety check: Pass | MIT | |
| K8s Security PoliciesCybereason-Public/owLSM | 280 | 12 repos | ~2k | Automated safety check: Pass | GPL-2.0 | |
| Payloadpayloadcms/payload | 45k | 5 repos | ~6.2k | Automated safety check: Pass | MIT | |
| Convex Setup Authspokvulcan/poker-planning | 114 | 8 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Cognitoitsmostafa/aws-agent-skills | 1.2k | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
coollabsio/coolify
A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.
Cybereason-Public/owLSM
Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.
payloadcms/payload
A skill your agent uses when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API).
spokvulcan/poker-planning
Sets up Convex auth, identity mapping, and access control. An agent skill from spokvulcan/poker-planning.
itsmostafa/aws-agent-skills
AWS Cognito user authentication and authorization service. An agent skill from itsmostafa/aws-agent-skills.
abpframework/abp
ABP permission system - PermissionDefinitionProvider, [Authorize] attribute, CheckPolicyAsync, IsGrantedAsync, ICurrentUser, IPermissionManager, multi-tenancy side.
Impertio-Studio/Frappe_Claude_Skill_Package
Deploy HTML/CSS websites to ERPNext/Frappe (v15/v16) as Web Pages via the REST API.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when designing multi-app Frappe architectures, deciding whether to split functionality into separate apps, or implementing cross-app communication patterns.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when debugging Frappe errors, using bench console for live inspection, analyzing tracebacks, or reading Frappe log files.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when receiving vague or unclear ERPNext/Frappe development requests that need interpretation.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when migrating a Frappe app between major versions, detecting breaking API changes, or resolving post-migration errors.
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when reviewing or validating Frappe/ERPNext code against best practices and common pitfalls.
Categories
A skill your agent uses when implementing the Frappe/ERPNext permission system. Frappe Core Permissions is an agent skill from Impertio-Studio/Frappe_Claude_Skill_Package. Use when implementing the Frappe/ERPNext permission system.
Frappe Core Permissions fits situations like: implementing the Frappe/ERPNext permission system; tasks that involve Authorization and RBAC.
Run `npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a claude-code`. Or copy the skill folder (skills/source/core/frappe-core-permissions in Impertio-Studio/Frappe_Claude_Skill_Package) into .claude/skills/frappe-core-permissions in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a codex`. Or copy the skill folder (skills/source/core/frappe-core-permissions in Impertio-Studio/Frappe_Claude_Skill_Package) into .agents/skills/frappe-core-permissions in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Impertio-Studio/Frappe_Claude_Skill_Package --skill frappe-core-permissions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frappe-core-permissions, .gemini/skills/frappe-core-permissions, .github/skills/frappe-core-permissions and .opencode/skills/frappe-core-permissions in your project.
SKILL.md names no scripts, command-line tools or credentials: Frappe Core Permissions is instructions for the agent only. Our summary lists: Python 3. Compatibility (from SKILL.md): Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16..
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Frappe Core Permissions is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Frappe Core Permissions: Configuring Horizon (coollabsio/coolify, 63k stars), K8s Security Policies (Cybereason-Public/owLSM, 280 stars), Payload (payloadcms/payload, 45k stars) and Convex Setup Auth (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Impertio-Studio (a GitHub organization) maintains it in Impertio-Studio/Frappe_Claude_Skill_Package, which has 189 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on September 17, 2026.
Source: Impertio-Studio/Frappe_Claude_Skill_Package on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.