Borrowing it
Nothing to install: this file belongs to ljcl/gaggiuino-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ljcl/gaggiuino-mcp/main/.agents/skills/backlog-sweep/SKILL.mdgit clone --depth 1 https://github.com/ljcl/gaggiuino-mcpWrote 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/ljcl/gaggiuino-mcp/backlog-sweep)<a href="https://agentmods.dev/skills/ljcl/gaggiuino-mcp/backlog-sweep"><img src="https://agentmods.dev/badge/skills/ljcl/gaggiuino-mcp/backlog-sweep/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/ljcl/gaggiuino-mcp/backlog-sweep"><img src="https://agentmods.dev/badge/skills/ljcl/gaggiuino-mcp/backlog-sweep.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 | $0.00100 | $0.01624 |
| Opus 5 | $0.00050 | $0.00812 |
| Sonnet 5 | $0.00020 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
backlog-sweep 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog sweep
Re-ground the issue backlog in the current code. Issues are written against a snapshot of the repo; every epic, tool removal, or shell extraction that merges afterwards silently invalidates file paths, line numbers, dependency notes, and sometimes whole premises. This sweep finds and fixes that drift so the next implementer isn't working from fiction.
Issues live in GitHub Issues and are triaged on the "gaggiuino-mcp backlog" Project board (see CLAUDE.md "Backlog and issue tracking" for labels and board fields).
When to run
- An epic,
feat!:breaking change, or wide refactor just merged (the trigger that most reliably strands open issues). - Before picking a batch of backlog work, so effort estimates rest on reality.
- On request ("triage the backlog", "is this issue still relevant?").
Procedure
-
Gather. List all open issues, and skim recently closed ones — open issues cross-reference them ("coordinate with #N", "after #N lands"), and whether #N closed as completed or not planned changes what the open issue should say. Note recent merged PRs / releases since the last sweep for context.
-
Verify each open issue against the code, not from memory. For every claim, grep or read the referenced file:
- File paths and line numbers ("
index.ts:256", "inmain.tsx") — refactors move code; shared extractions relocate it to another package entirely. - Existence claims ("no X exists", "nothing handles Y") — the gap may have been closed by an unrelated PR.
- Dependency framing ("once #N lands", "blocked on #N") — the dependency may have shipped (issue is now unblocked) or been closed not-planned (the coordination point no longer exists).
- Data sources and APIs the issue builds on — tools/endpoints get removed (e.g. the v2.0 read-tool removal) and the issue must point at what remains.
- Scope drift — a feature that shipped since filing may have changed what the issue needs to cover (e.g. a new default view widening an a11y issue).
- File paths and line numbers ("
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.
- 10d ago First seen · 110 lines · 100 tokens per session scan A e0e7c0ee0219
backlog-sweep is a skill published in the GitHub repository ljcl/gaggiuino-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 1,624 once invoked, about $0.0005 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.