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-pmgit 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-pm)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/lorekeeper-pm"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-pm/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-pm"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-pm.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 | $0.00042 | $0.01226 |
| Opus 5.5 | $0.00017 | $0.00490 |
| Sonnet 5.5 | $0.00008 | $0.00245 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
lorekeeper-pm 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lorekeeper PM
Product management workflow for the Lorekeeper project.
Roles
- PM (Akane) — drives product direction, files and prioritizes tickets, reviews shipped work, says yes/no on scope
- Dev — owns implementation, tests, and commit quality; raises blockers early; contributes to
lorekeeper-dev - Relay — Jason manually bridges PM ↔ dev. Repo holds details; relay is for intent/clarification only.
Core Principles
- High value, simple solutions — if a simpler way covers 80% of the value, do that.
- Don't overcomplicate — resist abstraction layers, new tools, or configurable options not needed yet.
- Don't act prematurely — if the problem isn't real (observable bug, measurable friction), don't solve it. File as proposal.
- Extend before create — prefer extending existing APIs/tools/scripts over new ones.
- Ship correctness before features — a working core beats an elaborate wishlist.
Backlog hygiene: Keep active backlog small (max 5 tickets). Push rest to S:proposal. When scoping down, update RICE scores and note rationale.
Commit Identity (PM)
git config --local user.name "Akane (PM)"
git config --local user.email "[email protected]"
Enforced by commit-msg hook. See commit-convention skill for full details.
Backlog Workflow
Full ticket lifecycle, numbering, scripts → load
backlog-managementskill.
Tickets live in backlogs/ as LKPR-N-slug.md. Completed → backlogs/done/. Numbering: sequential (highest+1), never fill gaps.
Weekly Planning
Once per week, pull up to 10 proposal tickets into active backlog:
- Review proposals in
backlogs/proposal/— pick high-value, unblocked items - Update status to
S:ready, set priority. Commit onchore/backlogbranch - Open PR against
main— auto-approved, no review needed. Jason squash-merges.
Mid-sprint goal shift
When Jason sets a new goal mid-sprint: 1) Analyze → map friction to fixes → estimates. 2) Get greenlight. 3) Execute: update statuses, commit on chore/backlog, PR.
What ships with it
1 file 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.
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 · 115 lines · 42 tokens per session scan A dc1458e417a1
lorekeeper-pm is a skill published in the GitHub repository Jessinra/Lorekeeper (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,226 once invoked, about $0.0002 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
project-switching
Project switching implementation in sidecar: project discovery, state management, UI flow, modal rendering, filtering, theme preview, and plugin reinitialization. Use when working on the project switcher feature, project management, worktree switching, or the project configuration system.
board-pilot
Board-driven implementation pipeline: polls a GitHub Project, arms an item when dragged into the trigger column, advances it stage by stage to a human-gated draft PR. Stages configured per project in workflow/projects/ .yaml. Trigger: "/board-pilot", "board pilot", "auto-implement from board", "pipeline runner".
bridge-overlay
Subscribe a Bridge to an ORG OVERLAY: a git repo publishing shared config (contexts, projects, mandants, org skills) as a flat mirror tree. Materializes copies via 3-way merge; your files always win. Trigger: "/overlay", "org overlay", "subscribe to overlay", "overlay status", "overlay diff".
github-projects-manager
The only write path to GitHub Projects V2, plus its governance: issue creation with board placement, field updates, batch transitions, board queries, audits, health checks, new-board setup. Reads schemas and rules from workflow/projects/.yaml. Trigger: "create issue", "set field", "board query", "audit board", "board…
debrief
Meeting and transcript processing: classifies meeting type, name corrections, extracts insights, generates protocols, proposes tasks. Full 8-phase flow (GitHub reconciliation, distribution email) or quick 5-phase. Trigger: "/debrief", "/debrief {path}", "/debrief --quick", "/debrief --all", "/debrief --date…
task-close-postmortem
Postmortem capture and bridge-improvement scan at task close: surfaces optional questions (time invested, what went well, what burned time, bridge gaps), writes frontmatter to STATUS.md, and generates proposals under work/learning/proposals/ for review via /bridge-learn. Trigger: "task done", "wrap up", "post-mortem"…