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 Jessinra/Lorekeeper --skill lorekeeper-code-reviewergit clone --depth 1 https://github.com/Jessinra/LorekeeperWrote 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/jessinra/lorekeeper/lorekeeper-code-reviewer)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/lorekeeper-code-reviewer"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-code-reviewer/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/jessinra/lorekeeper/lorekeeper-code-reviewer"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-code-reviewer.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 | $0.00032 | $0.01706 |
| Opus 5.5 | $0.00013 | $0.00682 |
| Sonnet 5.5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00171 |
Grade A, and why
lorekeeper-code-reviewer 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lorekeeper Code Review Patterns
Use this skill when reviewing any PR that changes src/lorekeeper/ runtime code, services, handlers, or MCP server. These are project-specific patterns that general-purpose review prompts miss.
Incident-driven: BLOCKER patterns 16-19 added after P0 Incident 2026-06-21 (Lorekeeper SQLite lock contention + infinite retry storm). See docs/incidents/IR-002-lorekeeper-sqlite-lock-contention.md. Patterns 20-24 added after LKPR-100 (server wiring, metrics, partial commits) and LKPR-67 (type migration, backup compatibility).
Load alongside github-code-review for a complete review session.
Severity Tiers
Every review comment must carry a severity label.
| Label | Tier | Merge impact |
|---|---|---|
blocker: |
🔴 BLOCKER | Must fix before merge |
issue: |
🟠 MAJOR | Fix before merge or create ticket |
suggestion: |
🟡 MINOR | Fix encouraged, deferrable |
nit: |
🔵 NIT | Optional, never blocks |
praise: |
✅ | Acknowledge good work |
Merge contract: PR is mergeable when all BLOCKERs resolved, all MAJORs resolved OR tracked, CI green, ≥1 human approval.
How to Use This Skill
- Holistic review — Before checking the diff, read every changed file in full, read adjacent files, and read the ticket/plan. Load
references/holistic-review.mdfor the full framework. - Pre-check —
git diff main...HEAD --name-only | grep -q "^src/lorekeeper/"→ RUNTIME or NON-CODE - Deleted-file check —
git diff main --name-status --diff-filter=D | grep -q "^D"— any deleted test file is BLOCKER unless replaced. - API divergence check — compare MCP tool signatures in
server.pyagainst the ticket ACs. Also scan the ticket's Required Updates section for checklist items. - RUNTIME PR → load
references/blocker-patterns.mdfor the 28 BLOCKER patterns - NON-CODE PR → load
references/non-code-pr-checklist.md - All PRs → check Maintainability (
references/maintainability-simplicity.md) - Migration PRs → check Backward Compatibility (
references/backward-compatibility.md) - README / user-facing docs — spot-check for duplicate sections, stale dates, merge artifacts
- Pre-merge → run
references/pre-deployment-checklist.md
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/backward-compatibility.md 3.7 KB
- references/blocker-patterns.md 32 KB
- references/holistic-review.md 5.8 KB
- references/maintainability-simplicity.md 3.6 KB
- references/non-code-pr-checklist.md 3.9 KB
- references/pr-237-review-patterns.md 4.3 KB
- references/pr-246-review-patterns.md 3.7 KB
- references/pre-deployment-checklist.md 2.1 KB
- references/stale-reviewer-comments.md 2.2 KB
- references/visual-browser-review.md 5.3 KB
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.
- 1mo ago First seen · 132 lines · 32 tokens per session scan A 0270a3eb3815
lorekeeper-code-reviewer is a skill published in the GitHub repository Jessinra/Lorekeeper (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,706 once invoked, about $0.0001 per session on Opus 5.5. 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
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
review-comments
Execute a feature-level review-comments cycle — aggregate unaddressed PR comments across every Feature.Repos PR, address or dismiss each one, and emit the standard handoff.
review-implementation-functionality-evidence
Implementation review Functionality/Evidence axis - audits plan satisfaction and verification evidence.
review-implementation-craft
Implementation review Craft axis - audits intrinsic code quality only.
review-implementation-cleanliness
Implementation review Cleanliness axis - audits change-set hygiene and pushability.
final-fix
Final-review fix pass that addresses requested changes and refreshes invalidated evidence.