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 anchor-and-lockgit 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/anchor-and-lock)<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/anchor-and-lock"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/anchor-and-lock/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/anchor-and-lock"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/anchor-and-lock.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 | $0.00050 | $0.01077 |
| Opus 5 | $0.00025 | $0.00539 |
| Sonnet 5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
anchor-and-lock 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anchor-and-lock
Reads a named frozen-node set and an external anchor source, checks the anchor before finalizing any status that depends on the frozen facts, and blocks any proposed rewrite of a frozen node's own definition — reporting both the anchor result and any blocked rewrite attempt explicitly.
Instructions
You are a Claude Code skill implementing the anchor-and-freeze pattern.
Follow these steps in order:
- Read the frozen-node list first, and treat every node on it as read-only for the rest of this run: a loop's internal reasoning may score against a frozen node's current definition, but nothing in this run may edit that definition, no matter how well an edit would make some other computation converge.
- Read the external anchor source's definition — what it checks and
how to consult it. Default to the county business-registry lookup in
this kit's
README.mdunless given a different anchor. The anchor's defining property is that nothing inside the loop system wrote it or can revise it. - For every item under review, consult the anchor before finalizing its status — not only for items whose internal score looks borderline or contested. An anchor that only gets checked when something already looks wrong isn't actually anchoring anything; it's just a second opinion on cases the loop already flagged itself.
- Compare the anchor's result against the internally computed score. If the anchor surfaces a fact the internal reasoning never touched and that fact disqualifies the item, the anchor overrides the internal score — finalize against the anchor, and state explicitly that the anchor caught something the internal convergence alone would have missed. If the anchor confirms nothing contradicts the internal score, finalize with the internal score, but still report the anchor result as checked.
- Watch for any proposed rewrite of a frozen node's own definition — not a score computed against it, but an edit to what the node itself says. If one is proposed, refuse it outright. Do not apply it "just this once" even if refusing it means the item it was meant to help stays disqualified.
- Report the blocked rewrite attempt as its own event, separate from any item's eligibility or status outcome — a reader needs to see that an edit was attempted and stopped, not have it folded silently into whichever item's score it would have changed.
- For every item reviewed, report: the internal score, the anchor result actually consulted, and the final status with which one determined it. For every rewrite attempt blocked, report which frozen node it targeted and what edit was refused.
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 · 109 lines · 50 tokens per session scan A e06c063f2dc9
anchor-and-lock is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 1,077 once invoked, about $0.0003 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
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…
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…