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/anthropic-api-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill anthropic-api-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 | $0.02104 |
| Opus 5 | $0.00005 | $0.01052 |
| Sonnet 5 | $0.00002 | $0.00421 |
| Haiku 4.5 | $0.00001 | $0.00210 |
Grade A, and why
anthropic-api-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 2d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anthropic API Compatibility Guidance
Use this skill when building or migrating integrations for the Messages API, hosted platform variants, Managed Agents, structured outputs, tools, streaming, prompt caching, model selection, or rate-limit handling. Treat the project's actual SDK types, API responses, and model metadata as authoritative when they differ from this rolling guidance.
Reference index
| Reference | Topics |
|---|---|
| Models and migrations | Model IDs, thinking, sampling, context, token budgets, migration contracts, refusals, images |
| Platforms and lifecycle | Retirement, model discovery, AWS surfaces, identity, compliance, enterprise administration |
| Structured outputs | JSON schemas, parse helpers, strict tools, schema limits, parsing safeguards |
| Tools and streaming | Eager input, stream aggregation and recovery, beta headers, hosted tools, MCP tunnels |
| Caching and rate limits | Cache breakpoints, TTLs, invalidation, pre-warming, token buckets, spend and workspace limits |
| Managed Agents | Agents, sessions, event streams, memory, secrets, schedules, budgets, advisors, repository skills |
Migration triage
Before changing a production target:
- Resolve the exact model ID and query
/v1/models/{model_id}for advertised context, output, and capability limits. - Remove assistant prefills and non-default sampling controls for targets that reject them.
- Move final structured output from top-level
output_formattooutput_config.format; keep the Python parse helper's convenience argument only when using that helper. - Recount tokens and retune
max_tokens, compaction, and cache breakpoints. - Audit tool versions, remove
undo_edit, and parse every tool input with a real JSON parser. - Treat
model_context_window_exceeded,max_tokens, andrefusalas separate stop conditions. - Remove retired beta headers and confirm whether the destination surface supports each remaining beta.
What ships with it
7 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.
- 2d ago First seen · 213 lines · 11 tokens per session scan A 6a0b976254a2
anthropic-api-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 2,104 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
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.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
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-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.