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 agentmods add skills/jerry0022/dotclaude/run-backlognpx skills add Jerry0022/dotclaude --skill run-backloggit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/run-backlog)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/run-backlog"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/run-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 | $0.00182 | $0.06183 |
| Opus 5 | $0.00091 | $0.03092 |
| Sonnet 5 | $0.00036 | $0.01237 |
| Haiku 4.5 | $0.00018 | $0.00618 |
Grade A, and why
run-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 4d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Backlog
Work off the project's planned backlog. Pick milestones (or loose issues), then refine → implement → test/QA → ship each selected item, one after another, until the backlog is done — so the user can lean back or go to bed and wake up to shipped work.
Architecture — standalone, compose-not-copy. This skill owns its own control
flow and is itself the ship instance. It does NOT modify run-autonomous
and never routes a ship through it — run-autonomous cannot ship by design,
and a task string never overrides that guardrail. Instead this skill reuses the
autonomous frame by calling the same plugin scripts (permission audit,
shutdown timer, resume schedule, watchdog, completion card) and referencing the
same deep-knowledge, and composes /concept, /ship, and the role
agents as building blocks. Full rationale + reuse table (dated design spec, kept
under its original name):
docs/superpowers/specs/2026-07-18-devops-burn-backlog-design.md.
Step 0 — Load Extensions
Silently check (do not surface "not found"):
~/.claude/skills/run-backlog/SKILL.md+reference.md{project}/.claude/skills/run-backlog/SKILL.md+reference.md- Merge: project > global > plugin defaults
Step 0.1 — Auto-Start / Resume Re-entry
If the incoming message starts with RUN_BACKLOG_AUTOSTART:, a presence-phase
timeout fired and the user is AFK. Step 1a arms this cron before the first
question, and every presence question re-arms it, so the timeout covers the
whole Präsenz phase — not just the final confirmation. Do NOT re-ask anything.
Parse phase, queue, milestones, shutdown, autoResume, burnMode, branch.
Pending-question guard: if an AskUserQuestion is still active when the
prompt arrives (the user is mid-answer), do NOT auto-start — re-arm a fresh
one-shot cron at now + 3min with the same prompt and keep waiting (log
"Autostart verschoben — offene Frage aktiv").
Otherwise branch on phase:
phase=gate— the full gate completed (permissions primed, queue + shutdown/resume chosen). Output once "Timeout — starte Backlog-Runner autonom.", skip Steps 1–3, jump to the Step 4 loop.phase=presence— the user left before finishing the gate. Timeout defaults apply and are not renegotiable:shutdown=yesalways. It is the only sensible default for a walked-away user (a report-only run nobody returns to just idles the PC all night).burnMode=noalways. The presence default is the normal sequential run; budget mode is a deliberate opt-in, never auto-enabled on a timeout.queue= the default encoded at arm time: every open milestone's issues (or every open loose issue when there are no milestones). Use a partial selection if one was already made before the timeout.- Skip Step 2 entirely. Concept decisions need the user and refine writes to
GitHub (presence-only). Park every
needs-decision/oversizeditem as a⏸ Rückfragefor the report; run only theready/ plain issues. - Run Step 3 non-interactively: permission audit + artifact hygiene, then arm
the lockout and the watchdog with
shutdown=yes. Skip the permission-audit question — proceed with already-granted permissions; anything not insettings.jsoncannot be primed AFK and falls to the per-issue late-permission protocol (deep-knowledge/autonomous-execution.md). Output once "Timeout in Präsenz-Phase — starte mit Defaults (alle offenen Milestones, Shutdown).", then jump to the Step 4 loop.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 421 lines · 182 tokens per session scan A 2920dd3e2127
run-backlog is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 6,183 once invoked, about $0.0009 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
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
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…
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…
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
project-init
Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…