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 recheck-mergesgit 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/recheck-merges)<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/recheck-merges"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/recheck-merges/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/recheck-merges"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/recheck-merges.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 | $0.00039 | $0.00920 |
| Opus 5 | $0.00019 | $0.00460 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
recheck-merges 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recheck-merges
Walks the graph's merge history and, for every past merge, decides whether new evidence leaves it standing or contradicts it outright. A contradicted merge gets reversed and the contradiction recorded; every other merge gets an explicit confirmation entry, never silence.
Instructions
You are a Claude Code skill implementing the reversible-merge-audit
pattern. For every merge in the history, in order:
- Read the merge's original basis first. Know exactly what claim the merge rested on (shared department and overlapping publication years, a matching ORCID, or whatever the history records) before looking at new evidence — you need to know what would actually contradict it.
- Gather every piece of new evidence tied to this merge. Evidence "tied to" a merge means it bears on whether the two originally-merged entities are really one thing — not just any new record that happens to mention one of the names.
- Test each piece of evidence against the merge's basis, specifically for direct contradiction. Direct contradiction means the evidence is incompatible with the merge being correct — for example, the same paper listing both name variants as two separate co-authors, which cannot happen if they're the same person. A record that's merely silent on the question, or that talks about one name variant without addressing the other, is not a contradiction.
- Reaffirming evidence is not grounds for anything except confirmation. If new evidence repeats or reinforces the merge's original basis (the same ORCID showing up again, for instance), that strengthens the case for leaving the merge alone — it must never be read as grounds to reverse.
- If you found a direct contradiction, reverse the merge. Split the canonical node back into its original separate entities, and record the specific evidence that triggered the reversal alongside it — a reversal with no stated evidence is not distinguishable from an accidental un-merge and should never be produced.
- If you found no direct contradiction, confirm the merge. Write an explicit confirmation entry — not just an absence of a reversal entry — naming which evidence was checked and that none of it contradicted the original basis. Every merge in the history needs one of these two outcomes; neither is optional and neither should be inferred by silence.
- Report every merge's outcome together, in history order: confirmed or reversed, and the evidence that decided it either way.
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 · 92 lines · 39 tokens per session scan A 413b4f8566d8
recheck-merges is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 15d ago), licensed MIT. It adds 39 tokens to every session and 920 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
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…
author-skill
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is specify) and NOT designing an agent loop…
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…
cpp
Use when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo…
gamedev-multiplayer
Use when adding multiplayer or netcode to a game — client-server vs P2P, server authority and anti-cheat, state replication vs RPCs, prediction and reconciliation, lag compensation, plus Godot 4 / Unity NGO / Unreal wiring. NOT single-player gameplay (that is godot, unity, unreal), NOT matchmaking or server hosting…
open-weights
Use when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping. Owns the license-class map (OSI-open versus custom-community versus non-commercial), the always-verify-the-model-card rule, size-to-VRAM…