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 Venkateshvenki404224/frappe-apps-manager --skill frappe-fixture-creatorgit clone --depth 1 https://github.com/Venkateshvenki404224/frappe-apps-managerWrote 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/venkateshvenki404224/frappe-apps-manager/frappe-fixture-creator)<a href="https://agentmods.dev/skills/venkateshvenki404224/frappe-apps-manager/frappe-fixture-creator"><img src="https://agentmods.dev/badge/skills/venkateshvenki404224/frappe-apps-manager/frappe-fixture-creator/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/venkateshvenki404224/frappe-apps-manager/frappe-fixture-creator"><img src="https://agentmods.dev/badge/skills/venkateshvenki404224/frappe-apps-manager/frappe-fixture-creator.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 | $0.00036 | $0.01550 |
| Opus 5 | $0.00018 | $0.00775 |
| Sonnet 5 | $0.00007 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
frappe-fixture-creator 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frappe Fixture Creator
Generate fixture JSON files for test data, master data, and initial site configuration in Frappe applications.
Global Rules
These Frappe conventions apply to everything this skill generates, and override any conflicting example below.
- Bench commands: use bare
bench(never./env/bin/benchor a full path). Always pass--site <site>explicitly — never run a barebench migrate/bench run-tests. Runbench startin the background and only if it isn't already running. Don't run discovery commands (which bench,bench --version). - DocType files live at
apps/<app>/<app>/<module>/doctype/<name>/<name>.json— the app name appears twice (directory + Python package) — with an empty__init__.pyalongside. Nevermkdirthe folder; write the JSON and runbench --site <site> migrateto create the structure. Don't addcreation,modified,owner,modified_by, ordocstatusas fields — Frappe manages them. - Database & ORM: prefer
frappe.qb.get_query()over rawfrappe.db.sql(). Usefrappe.db.get_all()for server logic (ignores permissions) andfrappe.db.get_list()for user-facing APIs (enforces them). Never usefrappe.db.set_value()on a field with validation or lifecycle logic — load the doc anddoc.save()so controller hooks run. Batch-fetch related records; never query inside a loop (N+1). - Never call
frappe.db.commit()in controllers, request handlers, background jobs, or patches — Frappe auto-commits on success and rolls back on uncaught errors. Flush manually only to make a write visible to a subsequentfrappe.enqueue()(or passenqueue_after_commit=True). - Permissions & APIs: put permission checks inside controller methods (enforced on every call path), not in API wrappers. Type-hint every
@frappe.whitelist()parameter so Frappe validates and casts it, and passmethods=[...]to pin the HTTP verb.
When to Use This Skill
Claude should invoke this skill when:
- User wants to create test fixtures
- User needs master data setup
- User mentions fixtures, test data, or setup data
- User wants repeatable site setup
- User needs demo or sample data
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 · 164 lines · 36 tokens per session scan A 99136ee44efa
frappe-fixture-creator is a skill published in the GitHub repository Venkateshvenki404224/frappe-apps-manager (27 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,550 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.