Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfilesnpx agentmods add skills/sfc-gh-eraigosa/dotfiles/mbo-planWrote 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/sfc-gh-eraigosa/dotfiles/mbo-plan)<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/mbo-plan"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/mbo-plan/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/sfc-gh-eraigosa/dotfiles/mbo-plan"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/mbo-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00260 | $0.05560 |
| Opus 5.5 | $0.00104 | $0.02224 |
| Sonnet 5.5 | $0.00052 | $0.01112 |
| Haiku 4.5 | $0.00026 | $0.00556 |
Grade A, and why
mbo-plan 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 1mo 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mbo-plan — plan an objective the MBO way
This repo keeps all objective-driven design work in docs/mbo/ as consistent
design → spec → plan artifacts, tracked in docs/mbo/index.md. This skill drives that
pipeline so every objective is captured, classified, routed to the right workflow, written
in the right place with the right shape, and tracked — instead of ad-hoc docs scattered around.
Source of truth: read docs/mbo/AGENTS.md first. It owns the pipeline, the task-type →
skill-workflow routing table, the slug/naming conventions, and the state lifecycle. This skill
is the procedure; that file is the policy. If they ever disagree, AGENTS.md wins.
Procedure
1 — Capture the objective
Find out what you're planning and pin a short slug (e.g. prping, sdk-migration):
- From an issue:
gh issue view <N> --json number,title,body,labels— the title/body is the objective; note the issue number forindex.md. - From a gss draft PR worktree (the common "I'm working on this right now" case): detect the
current branch and its PR —
gh pr view --json number,title,body,isDraft,headRefName(no arg uses the current branch). If there's no PR yet but you're on agss featureworktree, the branch name + the user's intent define the objective; offer to open the draft PR withgss prso there's something to attach to. - Derive the slug from the title (short, kebab-case, no date — dates live inside the docs and in
index.md).
2 — Classify and route
Decide the task type and pick the matching skill workflow from the routing table in
docs/mbo/AGENTS.md. The common cases:
| Objective is… | Workflow to run |
|---|---|
| a new skill | skill-creator:skill-creator → superpowers:writing-skills |
a dotfiles feature (shell/opt//ai//install) |
superpowers:brainstorming → superpowers:writing-plans → TDD |
a Go CLI under sdk/ |
brainstorming → writing-plans; mirror sdk/gss; engage go-team (go-goarch) for interfaces |
| a Go RPC/gRPC service | go-goarch (proto/boundaries) → writing-plans → go-godev/go-goqa |
| a UI / web piece | brainstorming (visual companion) → web-team → writing-plans |
| AWS infra/serverless | deploy-on-aws:* / aws-core:* / terraform-aws team |
| a large audit/migration | a Workflow fanned out to the architecture team → writing-plans |
What ships with it
3 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.
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.
- 1mo ago First seen · 291 lines · 260 tokens per session scan A 2473f7e96ca1
mbo-plan is a skill published in the GitHub repository sfc-gh-eraigosa/dotfiles (50 stars, last pushed yesterday), licensed Apache-2.0. It adds 260 tokens to every session and 5,560 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
there-there
Manage There There helpdesk tickets, contacts, and channels using the there-there CLI. Use when the user wants to list, view, reply to, search, or manage tickets; assign team members; manage tags; view contacts; or interact with there-there.app from the command line.
macos-release
Release a native macOS app to GitHub with DMG packaging and Sparkle appcast updates. Use this skill whenever the user wants to publish a new version, create a release, ship an update, push a release to GitHub, or update the appcast. Also trigger when the user mentions DMG creation, Sparkle signing, notarization…
review-pr
Review and merge GitHub pull requests for Spatie packages. Use when asked to review a PR, review a pull request, merge a PR, or when given a GitHub PR URL to review. Also triggers on 'review this PR,' 'check this pull request,' 'merge this,' or '/review-pr'. Uses gh CLI for all GitHub operations.
work
Handle issue/PR work items with worktree isolation. Triggered by "/work [issuelink|description]" to start focused work.
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.