Lorekeeper python.instructions.md

Python coding and review guidance for the Lorekeeper project, covering code style, errors, asynchronous work, data compatibility, logging, and tests.

In plain words
What is it for?
Use it when changing Python runtime code in src/, especially MCP server code, memory logic, persistence, or public behavior.
Why use it?
It highlights project rules and risks that general Python advice may miss, such as keeping protocol output separate from logs.

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/python
Clone the repo
git clone --depth 1 https://github.com/Jessinra/Lorekeeper

Made for: GitHub Copilot.

Per session 316 This file is loaded in full into every session.
When invoked 316 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00316 $0.00316
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash 6a3447b2fc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Lorekeeper python.instructions.md 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 yesterday.

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.

.github/instructions/python.instructions.md · 44 lines

What it actually says

Python / Lorekeeper Guidelines

Scope

Apply these rules to Python runtime code in src/.

Review focus

  • Prefer type-safe, mypy-friendly code.
  • Keep functions small and explicit.
  • Use existing project patterns instead of introducing new abstractions.
  • Avoid blocking work in async paths.
  • Keep exception handling visible; do not swallow errors silently.

Project conventions

  • Use uv run ... for tests and checks when needed.
  • For MCP server runtime code, keep stdout reserved for MCP protocol output.
  • Use structlog for logging.
  • Preserve data-model and schema compatibility unless a migration is included.

Repo-specific red flags

  • Any direct print() in runtime code is a bug unless it is intentionally part of a CLI tool.
  • Swallowed exceptions or vague except: blocks should be treated as review issues.
  • Changes to memory ranking, duplicate detection, scoring, or persistence should be reviewed as high-risk.
  • If a Python change alters public behavior, confirm the README and tests still match.

Testing expectations

  • New logic should have tests in tests/.
  • Add edge-case coverage for failures, not just happy paths.
  • Prefer focused unit tests over broad integration tests unless the change needs integration coverage.

Data and memory logic

  • Be careful with duplicate detection, search ranking, confidence updates, and deletion rules.
  • Treat changes to persistence or scoring as high risk.
  • Verify that any migration or backfill is safe to run more than once.
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. yesterday First seen · 44 lines · 316 tokens per session scan A 6a3447b2fc31

Subscribe to this mod's changes

Lorekeeper python.instructions.md is an instructions file published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 29d ago), licensed Apache-2.0. It adds 316 tokens to every session, about $0.0016 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.