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 ayeshakhalid192007-dev/graph-engineering-crash-course --skill score-and-mergegit clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-courseWrote 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/ayeshakhalid192007-dev/graph-engineering-crash-course/score-and-merge)<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/score-and-merge"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/score-and-merge/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/ayeshakhalid192007-dev/graph-engineering-crash-course/score-and-merge"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/score-and-merge.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 | $0.00037 | $0.00875 |
| Opus 5 | $0.00018 | $0.00438 |
| Sonnet 5 | $0.00007 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
score-and-merge 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
score-and-merge
Computes a numeric confidence score for every candidate merge pair from a fixed set of weighted signals, then splits the batch into auto-merged pairs and a review queue based purely on whether that score clears the threshold — never on how similar the pair "looks."
Instructions
You are a Claude Code skill implementing the confidence-scored-dedup
pattern. Follow these steps for every candidate pair in the batch:
- Read the scoring rule before touching any pair. Note each signal's weight (tax ID match, name token overlap, address match in this kit's rule) and the threshold that separates auto-merge from review queue. Treat these as fixed for the run — don't invent an extra signal or adjust a weight mid-pass because one pair "feels" borderline.
- Score each signal independently. For tax ID and address, this is a binary match/no-match. For name token overlap, compare the significant words in each name (ignoring corporate suffixes like "Co.," "Ltd," "Inc." when judging overlap, but still recording if only the suffix differs) and estimate the overlap fraction, then scale it by the signal's weight.
- Sum the signals into one total score per pair. Show your work — report each signal's contribution, not just the final number, so a reviewer can see why a pair scored the way it did.
- Compare the total to the threshold, and only the total. A single strong or weak signal must not override the sum — a pair with a matching tax ID but a mismatched address is decided by whether the sum of all three signals clears the threshold, not by treating the address mismatch as an automatic veto.
- Route pairs at or above threshold to auto-merge. Produce one canonical record per merged pair, and state which two source records fed into it.
- Route pairs below threshold to the review queue. Each queue entry must carry the pair, its total score, and the per-signal breakdown — never just "below threshold" with no explanation of which signals failed.
- Report both outputs together: the auto-merged set with scores, and the review queue with scores and signal breakdowns. A run that reports only the merges, or only the queue, has not finished this step.
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.
- 10d ago First seen · 85 lines · 37 tokens per session scan A 7cc980d552a6
score-and-merge is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 875 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 2026-08-31.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
mongodb
Use when modeling MongoDB documents (embed versus reference, the 16MB cap, bucket and subset patterns), choosing or fixing indexes (compound order by the ESR rule, partial, TTL, multikey, reading explain), writing aggregation pipelines that stay index-eligible, running multi-document transactions with retry, or…
postgresdb
Use when PostgreSQL engine behaviour decides the answer — schema and type design, index choice, reading EXPLAIN on a slow query, zero-downtime DDL and backfills, or ops (roles, RLS, pooling, vacuum, partitioning, PITR). PG16, ORM-agnostic. NOT portable query logic (that is sql), NOT a managed provider's platform…
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
db-migrations
Use when a schema change must ship without downtime — NOT NULL, rename, type change, or backfilling millions of live rows — for the expand-contract sequence and the lock/batching discipline that keeps each step from freezing prod. NOT lock internals or EXPLAIN (that is postgresdb), NOT drizzle-kit mechanics (that is…
dynamodb
Use when modeling or operating a DynamoDB table: deriving partition/sort keys from access patterns, single-table vs table-per-entity, adding a GSI/LSI, on-demand vs provisioned capacity, or diagnosing hot-partition throttling. NOT relational schema/SQL/EXPLAIN (that is postgresdb), NOT aggregation-pipeline document…