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 log-schema-versiongit 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/log-schema-version)<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/log-schema-version"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/log-schema-version.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 | $0.00045 | $0.00882 |
| Opus 5 | $0.00023 | $0.00441 |
| Sonnet 5 | $0.00009 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
log-schema-version 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 7d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
log-schema-version
Reads a pipeline's schema history and its list of extraction runs, and produces one log entry per schema version: its fields as introduced, and the complete set of run IDs that happened under it.
Instructions
You are a Claude Code skill implementing the versioned-schema-log
pattern. Follow these steps in order:
- Read the full schema history first. For each version, note its introduction date and its exact field list as of that introduction — not a running total, the list as it stood at that moment. Sort the versions by introduction date if they weren't given to you in order.
- Read the full run list. Default to the schema history and runs in
this kit's
README.mdunless the user gives you different ones. Note each run's id and the date it ran. Do not assume the list arrives sorted — treat run order in the input as meaningless and go strictly by date. - Assign every run to exactly one schema version, by comparing the run's date against each version's introduction date: a run belongs to the most recent schema version whose introduction date is on or before the run's date. A run happening on the exact day a new version is introduced belongs to the new version, not the old one.
- Do not merge field lists across versions. Each version's log entry reports only the fields that version itself defines. A later version adding fields does not retroactively change what an earlier version's entry lists.
- Account for every run in the input. A run with no schema version whose introduction date precedes it is an error condition — flag it rather than silently dropping it or guessing a version for it.
- Build one log entry per schema version: version id, introduction date, its field list as introduced, and the sorted list of run IDs assigned to it.
- Report every version's entry together, in version order, plus a note confirming the total run count assigned across all versions matches the total run count in the input — so a reader can see at a glance that no run was dropped or double-counted.
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.
- 7d ago First seen · 86 lines · 45 tokens per session scan A 566a4e7c089b
log-schema-version is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 882 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…
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…
community
Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…
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…
gamedev-physics
Use when working with a game engine's physics — rigid bodies, colliders, collision layers and masks, character controllers, joints, forces versus impulses, raycasts and shapecasts, or when a simulation is unstable (tunnelling, jitter, missed overlaps). Covers the Godot, Unity and Unreal equivalents. NOT rendering or…