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 rjroy/vibe-garden --skill backloggit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/rjroy/vibe-garden/backlog)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/backlog"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/backlog.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01933 |
| Opus 5 | $0.00026 | $0.00966 |
| Sonnet 5 | $0.00011 | $0.00387 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade A, and why
backlog 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 7d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Review Mode
You are now in Backlog Review Mode. Your role is to read all active issue files, assess their quality and readiness, and recommend the top 2-3 items to work on next based on priority, size, and definition quality.
Your Focus
- Issue discovery: Glob all
.lore/work/issues/*.htmlfiles - Status filtering: Include items with status
openorwontfix(excludedoneandclosed) - Quality analysis: Spawn backlog-analyzer agent to assess definition quality
- Recommendation: Present 2-3 best options with detailed rationale
Workflow
1. Discover Issue Files
Use Glob to find all issue files:
.lore/work/issues/*.html
If no files exist, stop and say:
No issue files found in .lore/work/issues/.
To get started, create your first issue with /compass-rose:add-item.
2. Parse Each Issue File
For each file, use Read to extract the meta tags from the <head> and the body text:
Meta tags to extract:
priority— e.g.,P0,P1,P2,P3size— e.g.,S,M,L,XLstatus— e.g.,open,wontfix,done,closeddate— creation datetitle— issue title (also available as<title>tag)
Body text: Extract the readable text content from the HTML body.
3. Filter by Status
Include items where status is open or wontfix. Exclude items where status is done or closed.
wontfix items are intentionally included. They are deferred, not done, and should surface if context changes.
If no items remain after filtering:
No open or deferred issues found in .lore/work/issues/.
All issues are either done or closed.
To add new work, use /compass-rose:add-item.
4. Prepare Data for Agent Analysis
Build a JSON array from the filtered items:
[
{
"filepath": ".lore/work/issues/fix-login-timeout.html",
"title": "Fix login timeout",
"priority": "P1",
"size": "S",
"status": "open",
"date": "2026-05-01",
"body": "<p>Users experiencing timeouts when submitting the login form...</p>"
}
]
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.
- 7d ago First seen · 240 lines · 53 tokens per session scan A db3ec5ea000a
backlog is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,933 once invoked, about $0.0003 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
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
backlog
Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…
recursive-spine-digest
Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators…
recursive-spine-bootstrap
Use when installing the recursive-spine tracking convention onto a repo — interviews for modules and dialect, then stamps labels, issue/PR templates, a CLAUDE.md/AGENTS.md tracking section, and cross-project board membership. Idempotent; degrades loudly on missing gh scopes; offers (never forces) plumb-line and…
recursive-spine-nudge
Use after a recursive-spine-digest sweep to select and deliver system-initiated nudges — 0–3 conversation-starters pushed to the owner about what is unblocked, aging, stalled, or newly connected. Every nudge ends in a question; the skill proposes conversations, never executes work.
recursive-spine-method
Use when a builder wants to learn or be reminded of the recursive-spine tracking convention — where work state lives (GitHub issues+milestones, never prose ledgers), the five principles, the module system, and how to design a repo's dialect. Pure knowledge; takes no actions.