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 0xagentkitchen/kitchenloop --skill kitchenloop-backloggit clone --depth 1 https://github.com/0xagentkitchen/kitchenloopWrote 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/0xagentkitchen/kitchenloop/kitchenloop-backlog)<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/kitchenloop-backlog"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/kitchenloop-backlog/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/0xagentkitchen/kitchenloop/kitchenloop-backlog"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/kitchenloop-backlog.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 | $0.00000 | $0.01555 |
| Opus 5.5 | $0.00000 | $0.00622 |
| Sonnet 5.5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
kitchenloop-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 2mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KitchenLoop: Backlog
Scan the backlog, evaluate tickets, promote to todo queue, maintain balance.
Triggers
kitchenloop backloggroom backlogpromote tickets
Overview
The Backlog phase keeps the todo queue healthy. It scans all open tickets, scores them on urgency/accessibility/impact, promotes the best candidates to the todo queue, and retires stale tickets. The goal is to maintain a todo queue of 5-8 tickets with good category balance.
Procedure
Step 1: Read Context
- Load
kitchenloop.yaml-- readticketing,paths, andruntime. - Read loop state at
paths.loop_statefor iteration context. - Read
paths.patternsfor known patterns that inform prioritization.
Step 1.5: Abandoned Fix PR Scan
Scan for tickets whose fix PRs were closed without merging — these bugs are still live:
gh pr list --state closed --limit 50 \
--json number,title,body,state,mergedAt \
--jq '.[] | select(.mergedAt == null)'
For each closed-not-merged PR:
- Extract the ticket ID from the PR title/body (look for #N references)
- Check if the ticket is still open (todo/in_progress/in_review)
- If yes: promote back to "todo" with comment: "Fix PR #N was closed without merging. Bug is still live on main. Re-promoting for execution."
- If the ticket was already closed: reopen it
This prevents bugs from going unfixed when AI-generated fix PRs are silently abandoned.
Step 2: Inventory Current State
Count tickets by state:
# Todo queue
gh issue list --label "{ticketing.github.state_labels.todo}" --json number,title,labels
# In progress
gh issue list --label "{ticketing.github.state_labels.in_progress}" --json number,title
# In review
gh issue list --label "{ticketing.github.state_labels.in_review}" --json number,title
# Full backlog (unlabeled state)
gh issue list --state open --json number,title,labels,createdAt,body --limit 200
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.
- 2mo ago First seen · 200 lines · 0 tokens per session scan A 5008a87c48fa
kitchenloop-backlog is a skill published in the GitHub repository 0xagentkitchen/kitchenloop (23 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,555 tokens. 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 2026-08-30.
kitchenloop-backlog compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kitchenloop-backlog0xagentkitchen/kitchenloop | Skill | 23 | 7mo ago | MIT | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |