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 skills/nevaberry/nevaberry-plugins/alembic-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill alembic-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWhat 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 | $0.00011 | $0.01781 |
| Opus 5 | $0.00005 | $0.00890 |
| Sonnet 5 | $0.00002 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
alembic-knowledge-patch 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 3d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alembic Knowledge Patch
Use this skill when changing an Alembic project, reviewing generated migrations, upgrading Alembic, extending its CLI or operation system, or diagnosing revision graph and backend-specific DDL behavior.
Inspect the project's pinned Alembic, Python, and SQLAlchemy versions before applying version-dependent advice. Prefer the project's code, tests, and observed database behavior when they disagree with general guidance.
Reference index
| Reference | Topics |
|---|---|
| Compatibility and configuration | Runtime and build requirements, the yanked wheel, TOML configuration, path parsing, and path APIs |
| Autogenerate and rendering | Indexes, constraints, operation rendering, comparators, filtering, and plugins |
| Operations and DDL | Conditional DDL, comments, inline keys and references, and offline version-table behavior |
| Revisions, CLI, and extensions | Revision paths and identifiers, head checks, merge splicing, command registration, and operation implementations |
Upgrade triage
Avoid the yanked 1.15.0 wheel
Do not deploy Alembic 1.15.0. Its wheel omitted migration template files after the packaging move to PEP 621. Use 1.15.1 or later in that series.
Enforce the applicable runtime floor
- Alembic 1.15 requires Python 3.9+ and SQLAlchemy 1.4+.
- Alembic 1.17 requires Python 3.10+.
- Alembic 1.18 requires SQLAlchemy 1.4.23+.
Check source-build environments separately: the 1.16 series raised its setuptools build requirement to 77.0.3.
Update path parsing deliberately
For new or updated INI files, set:
[alembic]
path_separator = os
path_separator replaces version_path_separator, applies to both
version_locations and prepend_sys_path, and uses os.pathsep when set to
os. An omitted setting preserves legacy splitting with a deprecation warning.
What ships with it
5 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.
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.
- 3d ago First seen · 216 lines · 11 tokens per session scan A fe8e905b213d
alembic-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 1,781 once invoked, about $0.0001 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
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
omh-backend
This is a Hermes-native backend workflow skill.
redteam-sqli-detail-pack
Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…