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 agentmods add instructions/jessinra/lorekeeper/pythongit clone --depth 1 https://github.com/Jessinra/LorekeeperWhat 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 | $0.00316 | $0.00316 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
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.
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
structlogfor 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.
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.
- yesterday First seen · 44 lines · 316 tokens per session scan A 6a3447b2fc31
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.
Other instructions, from other repositories
hindsight CLAUDE.md
Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.
EverOS CLAUDE.md
Claude Code instructions for EverMind-AI/EverOS, covering everos — md-first memory extraction framework, quick commands, architecture, engineering practices and branch strategy.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
dense-mem AGENTS.md
Instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.
Meterless AGENTS.md
Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.
open-bridge AGENTS.md
Instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.