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 ahmedawan-oracle/claude-code-plugins --skill incremental-mechanismgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/ahmedawan-oracle/claude-code-plugins/incremental-mechanism)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/incremental-mechanism"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/incremental-mechanism.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.01700 |
| Opus 5 | $0.00069 | $0.00850 |
| Sonnet 5 | $0.00028 | $0.00340 |
| Haiku 4.5 | $0.00014 | $0.00170 |
Grade A, and why
incremental-mechanism 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
incremental-mechanism
Choose the cheapest refresh mechanism that is still correct for the node. Refresh cost matters, but a fast strategy that can silently miss financial changes is not acceptable.
This skill is for refresh-strategy decisions only. It inspects the existing content-pack node, verifies source behavior against the live tenant, recommends a mechanism, and changes pack metadata only after the user confirms. It never changes a node's business grain, natural key, or output contract.
When to use
- "Can this node be incremental?"
- "Why does this table full-extract or rebuild every incremental run?"
- "Make this mart cheaper to refresh."
- A new bronze source or mart needs an evidence-backed refresh strategy.
- A cost review identifies a node whose incremental run cost is close to a seed.
When not to use
- The request is to run a seed or incremental pipeline. Use the run-oriented seed/incremental skills or the CLI.
- A drift gate or missing source column failed. Route to the drift/authoring workflow first, then return here only if the refresh strategy itself is in question.
- The user wants a new mart or dimension designed from scratch. Author the node first, then use this skill to verify the refresh mechanism.
Mechanism ladder
Pick the highest rung supported by both live evidence and source semantics.
| Rung | Mechanism | Use when |
|---|---|---|
| 1 | Native BICC incremental (incrementalCapable: true) |
The live probe shows BICC honors fusion.initial.extract-date, and the source has a reliable lineage timestamp for every meaningful change. Best fit for transaction and master-data PVOs. |
| 2 | LUD datastore filter | Native BICC cursoring is unavailable, but a live-verified last-update-date column is trustworthy as a row-level change cursor. Treat as opt-in until verified on the customer's tenant. |
| 3 | Period-window datastore filter | The source is a high-volume period snapshot where row-level cursor trust is not proven, but a period column can safely limit each incremental run to recent open periods plus periodic full reseeds. |
| 4 | Replace | No reliable change signal exists, or the node is intentionally rebuilt because it is small, date-anchored, or aggregate-shaped in a way that makes partial merge unsafe. |
What ships with it
1 file 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.
- 6d ago First seen · 166 lines · 139 tokens per session scan A deee5232b976
incremental-mechanism is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 1,700 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…