Lorekeeper copilot-instructions.md

Repository instructions for reviewing Lorekeeper code, including required labels for review comments and rules for deciding whether a pull request can be merged.

In plain words
What is it for?
Use them when reviewing Lorekeeper changes for security bugs, data errors, architecture violations, performance issues, missing tests, style concerns, or positive patterns.
Why use it?
They make review feedback consistent and show which problems must be fixed before merging.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/jessinra/lorekeeper/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Jessinra/Lorekeeper

Made for: GitHub Copilot.

Per session 1,866 This file is loaded in full into every session.
When invoked 1,866 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01866 $0.01866
Opus 5 $0.00933 $0.00933
Sonnet 5 $0.00373 $0.00373
Haiku 4.5 $0.00187 $0.00187

Measured 3d ago against content hash 3401f684f348, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Lorekeeper copilot-instructions.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Blocking I/O inside `async def` (`time.sleep()`, `requests.get()`, sync file reads)
.github/copilot-instructions.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lorekeeper Copilot Code Review Instructions

These instructions guide Copilot (and any AI reviewer) for this repository.


Review Severity Tiers

Every review comment must carry an explicit severity label. Unlabeled comments are unclear and tend to be ignored.

Tier Label Merge impact When to use
🔴 BLOCKER blocker: Blocks merge. No exceptions. Security bug, data corruption, MCP contract violation, architectural constraint violation
🟠 MAJOR issue: Fix before merge OR create follow-up ticket Logic error, N+1 query, missing test on critical path, blocking I/O in async
🟡 MINOR suggestion: Fix encouraged, deferrable Non-idiomatic code, weak naming, missing docstring
🔵 NIT nit: Completely optional, never blocks Style preference, alternative valid implementation
✅ PRAISE praise: n/a Good patterns — use actively

Merge contract — a PR is mergeable when:

  • ✅ All BLOCKER comments resolved
  • ✅ All MAJOR comments resolved OR a follow-up ticket created
  • ✅ CI gates green (lint, type check, tests, PR size)
  • ✅ At least 1 human approval

Conventional Comments Format

Every comment must use this format:

<label> [(<decorator>)] [<file>:<line>]: <subject>

[1–3 line explanation]
[Optional: code example showing the fix]
Rationale: <why this matters>

Good example:

blocker: (src/lorekeeper/server.py:78): print() call leaks to MCP protocol stdout.
Replace with: structlog.get_logger().info("message")
Rationale: stdout is reserved for MCP JSON-RPC. Any stray print() corrupts the protocol stream.

Read the full file on GitHub · 190 lines

Changes

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.

  1. 3d ago First seen · 190 lines · 1,866 tokens per session scan A 3401f684f348

Subscribe to this mod's changes

Lorekeeper copilot-instructions.md is an instructions file published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,866 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.