Nexent is a zero-code platform for creating AI agents from natural-language instructions, combining tools, skills, memory, orchestration, constraints, feedback loops, and control planes. It is intended for people who need to build and deploy agents without writing orchestration code. The catalogue entries are rules and skills for working with Nexent.
Borrowing it
Nothing to install: this file belongs to ModelEngine-Group/nexent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ModelEngine-Group/nexent/develop/.agents/skills/nexent-test-assets/SKILL.mdgit clone --depth 1 https://github.com/ModelEngine-Group/nexentWrote 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/modelengine-group/nexent/nexent-test-assets)<a href="https://agentmods.dev/skills/modelengine-group/nexent/nexent-test-assets"><img src="https://agentmods.dev/badge/skills/modelengine-group/nexent/nexent-test-assets/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/modelengine-group/nexent/nexent-test-assets"><img src="https://agentmods.dev/badge/skills/modelengine-group/nexent/nexent-test-assets.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 | $0.00068 | $0.01531 |
| Opus 5.5 | $0.00027 | $0.00612 |
| Sonnet 5.5 | $0.00014 | $0.00306 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
nexent-test-assets 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexent formal test assets
Maintain one traceable chain:
Requirement or Bug -> Feature -> D1-D5 Case -> case-local execution.yaml -> Fixed Script -> Result.
Paths are relative to the repository root. Authoritative assets live under test-e2e/features/<Feature-ID>/feature.yaml, test-e2e/cases/<Case-ID>/case.yaml, and test-e2e/changes/<type>/. Each implemented Case owns execution.yaml and its primary test script in the same Case directory. features/<Feature-ID>/cases.md, test-e2e/infra/generated/registry.json, and the Excel workbook there are generated read-only views; no hand-maintained central manifest or cross-platform symlink is needed.
Boundaries
- Do not reuse or register tests from
test/backend,test/sdk, ortest/ext_componentsas formal D1 cases. Those are Legacy UT. - Traditional UT is permanently maintained alongside this suite, not a transition baseline to replace. Assess both suites for every product change; use
nexent-python-testsfor Python UT. UT-only proof can satisfy a unit acceptance requirement in the change record, but cannot count as execution of a formal Case. - Preserve all existing D1 definitions/scripts, including unit-oriented and overlapping Cases. Do not bulk delete, retire, migrate or relabel them. New D1 should add component-contract evidence beyond unit assertions; read case-design.md for the UT/D1/D3 boundary. A feature need not add a D1 if UT and higher-layer tests already supply the necessary proof.
- A Case's primary script lives beside its
case.yaml; shared framework helpers live undertest-e2e/infra/automation/. Do not make a shared helper the primary Case binding. - Design cases before product implementation. Implement fixed scripts and case-local
execution.yamlafter product implementation, except an intentional bug reproduction may be written earlier. - If product code is already complete and the request is to add missing tests, use
test-backfillrather than restarting product implementation. Inspect actual UT assertions before creating formal Cases; sufficient unit proof needs no duplicate D1 or formal Case ID. - Update only affected Case directories, then validate the complete derived registry.
- In bugfix mode, reuse existing coverage before adding Cases; zero additions is valid. A missing SPEC or unavailable test baseline does not trigger whole-feature test generation. Follow bugfix.md for impact selection.
- Do not edit the generated Excel workbook directly.
- Do not encode secrets, personal absolute paths, or environment-specific runtime IDs in formal cases or scripts.
- Ordinary Cases need no deployment grouping fields. Only Cases requiring a different product deployment belong in the small repository
test-e2e/infra/config/deployment-exceptions.yamlcatalog; read deployment-exceptions.md for mode-sensitive design or execution. Requiring a Mock alone does not imply a deployment switch. - Business tests must not depend on a specific SQL file path. Test migration behavior only at the D5 deployment boundary.
- Store change records by type under
test-e2e/changes/{requirements,bugs,refactors,test-fixes}/. Changes record affected IDs; the lasting Feature and Case definitions remain in their respective directories.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acceptance-integrity.md 4.0 KB
- references/bugfix.md 5.1 KB
- references/case-design.md 5.1 KB
- references/deployment-exceptions.md 3.0 KB
- references/lifecycle.md 3.5 KB
- references/manifest.md 2.0 KB
- references/migration.md 714 B
- references/mock-profiles.md 703 B
- references/runtime-migration.md 2.7 KB
- references/test-backfill.md 5.1 KB
- references/test-implementation.md 2.2 KB
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.
- 6d ago Changed · +1 lines ce38bc49e3e7
- 17d ago Changed · +8 lines · -9 tokens per session 56759b4f6860
- 1mo ago First seen · 59 lines · 77 tokens per session scan A fffbf5a864f2
nexent-test-assets is a skill published in the GitHub repository ModelEngine-Group/nexent (6,085 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,531 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
attendance-signin-sheet
A spreadsheet generator for printable attendance or meeting sign-in sheets. It turns a list of names into rows with columns such as signatures, dates, departments, or employee IDs.
composio-delivery
Delivers the finalized analyst brief to Slack, Notion, Google Sheets, and Gmail via authenticated Composio tools. Use whenever a completed, grounded brief must be distributed and logged.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…