Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add infohata/mind-vault/plugin install mvWrote 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/infohata/mind-vault/sprint-auto)<a href="https://agentmods.dev/skills/infohata/mind-vault/sprint-auto"><img src="https://agentmods.dev/badge/skills/infohata/mind-vault/sprint-auto/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/infohata/mind-vault/sprint-auto"><img src="https://agentmods.dev/badge/skills/infohata/mind-vault/sprint-auto.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 | $0.12788 |
| Opus 5 | $0.00000 | $0.06394 |
| Sonnet 5 | $0.00000 | $0.02558 |
| Haiku 4.5 | $0.00000 | $0.01279 |
Grade A, and why
sprint-auto 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 5d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sprint-auto
Autonomous wrapper around the full sprint workflow (/plan → /work → /wrap → review-loop → integration phase → /compound, where the review-loop pass is one /review-loop <PR> $SPRINT_AUTO_REVIEW_ENGINE call carrying the configured engine(s) over the wrapped PR — single-review cadence, IDEA-015 — or is skipped when engine is none) for unattended overnight execution on a VPS. Takes a curated list of IDEAs that the human has pre-cleared as low-risk and runs each one through the per-IDEA loop, then runs all of them through a batch-level integration phase: a long-lived integration branch is the base ref for every per-IDEA PR. Per-IDEA PRs target integration; the integration phase merges them sequentially, lands compatibility / conflict-resolution patches as visible commits, validates the integrated state with union + full-suite tests + the configured review loop, and opens a single non-draft [INTEGRATION] PR that targets the parent (main / sprint-*). When the human merges that one PR, every per-IDEA PR auto-closes as a merged ancestor.
The skill stops at the one HITL boundary that matters: merge to a protected branch.
This skill is not a substitute for human review — it is a throughput multiplier for ideas where the human has already decided "no harm trying". The human still reviews. The skill's job is to close the gap between "I have 10 low-risk IDEAs in the backlog" and "I have 10 IDEA-isolated per-PR PRs (each drained through the configured review engine in one post-wrap review pass) plus one integration PR (drained through the same engine on the integrated state) waiting on my desk, with cross-project learnings already promoted to mind-vault as their own review-looped PRs".
v3.2 (current) vs v3.1: v3.1 had per-IDEA PRs target the parent (main / sprint-*), then forward-synced the integration's content back into each per-IDEA PR after S11.10. The result was N PRs all carrying the entire batch's diff — atomic-batch-merging at the cost of "N identical PRs" UX confusion. v3.2 inverts the routing: integration is the base ref, per-IDEA PRs stay IDEA-isolated for review, integration PR is the single merge gate. Forward-sync (S11.11) and per-PR re-review (S11.12) are deleted — they only existed to compensate for the v3.1 routing.
What ships with it
12 files 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.
- assets/auto-run-log-template.md 12 KB
- assets/setup_playwright.sh.template 23 KB
- assets/sprint-auto-bootstrap.sh.wrapper 2.9 KB
- assets/sprint-auto-hooks.sh.example 2.9 KB
- IDEA_integration_branch.md 38 KB
- references/escalation-policy.md 12 KB
- references/integration-conflict-resolutions.md 11 KB
- references/integration-stage.md 25 KB
- references/PARALLEL_WORKTREE_DOCKER.md 26 KB
- references/post-pr-sequence.md 35 KB
- references/safety-gates.md 14 KB
- references/worktree-lifecycle.md 15 KB
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.
- 5d ago Changed 90f20fc3372b
- 9d ago First seen · 343 lines · 0 tokens per session scan A 98a871e8244a
sprint-auto is a skill published in the GitHub repository infohata/mind-vault (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 12,788 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 2026-08-31.
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.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.