Borrowing it
Nothing to install: this file belongs to band-app/band. 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/band-app/band/main/.claude/skills/backlog-burner/SKILL.mdgit clone --depth 1 https://github.com/band-app/bandWrote 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/band-app/band/backlog-burner)<a href="https://agentmods.dev/skills/band-app/band/backlog-burner"><img src="https://agentmods.dev/badge/skills/band-app/band/backlog-burner/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/band-app/band/backlog-burner"><img src="https://agentmods.dev/badge/skills/band-app/band/backlog-burner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 418 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00105 | $0.08098 |
| Opus 5.5 | $0.00042 | $0.03239 |
| Sonnet 5.5 | $0.00021 | $0.01620 |
| Haiku 4.5 | $0.00011 | $0.00810 |
Grade A, and why
backlog-burner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Burner — Master Orchestrator
Supervises all worktrees in a repo. On every run: scans the backlog, checks each worktree's chat state, dispatches work to idle agents, merges PRs that are ready, and cleans up finished worktrees.
This skill is designed to run as a repo-scoped cronjob on the main branch. Set it up with:
band cronjobs create <repo> \
--name "Backlog Burner" \
--prompt "Run /backlog-burner" \
--cron "*/10 * * * *" \
--scope repo
What the burner picks up
Only GitHub issues with the backlog-burner label are in scope. Every other issue is invisible to this skill. Add the label to opt an issue into automated processing; remove it to take an issue back under manual control.
Division of labor
Worktree agent (inside each per-issue worktree) — narrow job:
- Implement the issue.
- Run
/review-and-applyto lint/clippy/test and apply any fixes it surfaces. - Commit and push.
- Create the PR (
gh pr create --base main --fill --body "Closes #$N"). - Stop. Wait for the next nudge.
Burner (this skill, running as a cronjob) — orchestration:
- Creates the worktree and the initial chat (no
/band-startneeded — the burner already has all the context). - On every tick: scans PR state, nudges the agent when there's
blocker-severity feedback or CI failures, and merges directly (from outside the worktree) once CI is green and no blocker remarks remain. - Cleans up the worktree after merging.
The agent never invokes /finish-pr. PR creation is the agent's last step before it stops; everything after that — CI watching, feedback dispatch, merge, cleanup — happens at cron cadence from the burner.
There is no human approval gate. A PR is mergeable as long as there are no blocker-severity remarks and CI is green. Findings tagged nit or suggestion are advisory — they never block the merge. Even nits are capped: the burner dispatches at most 3 non-blocker iteration rounds before merging anyway (see step 3 case (d) and the review-round chat label).
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.
- 25d ago Changed · +3 tokens per session dfb7b0fb8f1e
- 26d ago Changed 32aa15a07b90
- 2mo ago First seen · 559 lines · 102 tokens per session scan A 2b63462ac559
backlog-burner is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 8,098 once invoked, about $0.0004 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
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.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.