Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Jessinra/Lorekeepernpx agentmods add skills/jessinra/lorekeeper/sprint-reviewWrote 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/sprint-review)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/sprint-review"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/sprint-review/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/sprint-review"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/sprint-review.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 | $0.00033 | $0.00831 |
| Opus 5 | $0.00016 | $0.00415 |
| Sonnet 5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
sprint-review 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 9d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Review
Regular backlog review session to triage proposals, validate ticket readiness, and batch-promote validated tickets to dev.
Cadence
Run a sprint review at least weekly, or whenever there are enough proposals to triage. The goal is to keep the dev queue healthy — not to rush work.
Process
1. Review all proposals
Pull up all tickets in S:proposal status:
cd ~/Code/lorekeeper
./scripts/lorekeeper-backlog.sh proposal
For each proposal, ask:
- Is the problem still valid? — has anything changed since this was filed?
- Is the solution still the right one? — any new context that changes the approach?
- Is the ticket complete enough? — clear problem statement, acceptance criteria, affected files?
2. Validate readiness (the critical step)
Before promoting any ticket to S:ready, verify:
- Problem still exists — not solved by another change, not obsolete
- Solution still makes sense — not superseded by a better approach since filing
- Acceptance criteria are concrete — each AC is verifiable, not vague
- Affected files listed — backend paths + dashboard changes (or
_none_) - No open blockers — dependencies are listed and resolved
- Priority still correct — not over/under-prioritized relative to other active tickets
- No duplicate — check the rest of the backlog for overlapping ideas
If a ticket fails any check: update it, defer it (S:deferred), or cancel it (S:cancelled) with a note why. Don't promote stale tickets.
3. Triage actions
| Verdict | Action |
|---|---|
| ✅ Ready | Promote to S:ready, ensure proper P: priority label |
| ⏳ Needs more info | Tag as S:deferred with a note on what's missing |
| ❌ Not doing | Tag as S:cancelled with rationale |
| 📋 Merge into existing | Close as duplicate, link to parent ticket |
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.
- 9d ago First seen · 87 lines · 33 tokens per session scan A 6fc4981e3753
sprint-review is a skill published in the GitHub repository Jessinra/Lorekeeper (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 831 once invoked, about $0.0002 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 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
Generic, board-driven implementation pipeline: polls a GitHub Project on a schedule, ARMS an item the moment a human drags it into the configured trigger column, then advances it one stage per tick — each stage a Bridge primitive (skill / workflow / agent / cmd) — and STOPS at a human-gated draft PR. The engine is…
bridge-overlay
Subscribe a Bridge to an ORG OVERLAY — a git repo an organisation publishes that ships its shared config (contexts, projects, mandants, accounts, org skills/agents/standing-orders, an ecosystem fragment) as a flat mirror tree. /overlay add sparse-clones the overlay, validates its manifest, previews a per-file plan…
github-projects-manager
Execute GitHub Projects V2 operations — issue creation with automatic project board placement, custom field updates (single-select, text, number, date), batch field transitions, board queries, and board-hygiene audits (coverage: open issues not on the board; reconciliation: board Status vs the issue's real…
task-close-postmortem
Postmortem capture + bridge-improvement scan at task close. Surfaces six optional questions (time invested, estimate vs actual, what went well, what burned time, where the bridge fell short, concrete improvement proposal), writes structured frontmatter back to STATUS.md, and generates proposal files under…
bridge-greeting
Context-aware terminal greeting (MOTD) for Bridge instances — renders a per-instance logo, palette, today's filtered calendar, the instance's "Doing" board and uncommitted work, resolved from which org folder the terminal was opened in. Includes gen-logo.py (ANSI-Shadow logo generator from a word) and the branding…