claude

shotos-core

The SHOTos core: six stages, four rules, twelve controls, 28 skills, nine role agents and a claim-check Stop hook that tests what agents say they did.

1 on GitHubby Liam McDowellv1.15.0MITupdated 5 days ago
/

Plugin shotos-core from marketplace shotos in SHOTClubhouse/shotos. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (28)

  • agree-acceptance

    Agrees what done looks like before work starts: concrete checks, who accepts, what the agent must not do, plus examples (one failing) for variable output. Use when starting any task whose result someone else will rely on.

  • baseline

    Records how things are today before a change: the measures that matter, each value's source and date, and \"not measured\" where no data exists. Use when starting a change later judged better or worse, or before setting a target.

  • capture-the-problem

    Turns rough notes, a complaint, an idea or a request into a problem statement: who is affected, the cost, what is unknown and the cheapest first test. Use when a request describes a solution rather than a problem.

  • cross-agent-review

    Pairs a lead agent with an independent reviewer (a different person, a different model, or the same model in a fresh session), both given the same acceptance card and evidence. Use when work is medium or high risk or leaves the team. The owner decides.

  • decision-record

    Writes a short record of a decision: context, options, decision, who decided, evidence, what would change it and review date. Use when a supplier, design, policy or scale-pivot-stop call needs recording, or someone asks \"why did we do this?\"

  • delivery-metrics

    Measures the four DORA delivery keys from existing git history, deploy logs and incident notes, plus eval pass rate, cost per accepted task and edit rate for AI features. Use when asking how delivery is going. Not for ranking people.

  • enablement-plan

    Plans how a team becomes self-sufficient with a new process or agent-assisted way of working: capability matrix, pairing, train-the-trainer, and an exit test of one cycle without the builders. Use when results still depend on the people who built them.

  • eval-set

    Builds a small eval set for AI output: 5 to 20 real examples, what each answer must and must not contain, one failing case, how to grade. Use when relying on AI-written text or classifications, or changing their prompt.

  • evidence-handoff

    Hands work to a person, team, agent or later session with state, evidence, open decisions and next step intact. Use when a receiving owner needs to take over work with its evidence and open decisions. Final task claims use report-with-evidence; Track results use evidence-pack.

  • evidence-pack

    Builds the Track evidence pack with sourced results, the Scope baseline and measurement gaps. Use after a pilot or when someone claims an improvement without numbers. A named owner decides whether to proceed to Own, pivot or stop.

  • example-mapping

    Runs an example-mapping session: story, rules, concrete examples, open questions, then settled examples as Given/When/Then. Use when building anything with business rules, or when a request is too vague to turn into checks.

  • experiment-plan

    Plans the smallest test of a hypothesis: method, sample, duration, cost, success and stop criteria, and who decides. Use when a hypothesis card exists and before building, buying or rolling out the full solution to find out whether it works.

  • graduation-ladder

    Decides how much autonomy a repeated task class has earned from logged acceptance outcomes: draft only, automatic with notice, or silent. Use when reviewing a task class or considering less supervision. Never loosens send, spend, delete or publish limits.

  • hypothesis-card

    Turns an idea into a testable bet: \"We believe X will result in Y, and we will know because Z changes\", with measure, baseline, target and stop result. Use when a benefit is assumed, or someone says \"this will help\".

  • label-the-proof

    Labels each part of a report as literal, inferred or illustrative, and edits the one canonical file in place, never a new copy, since version history keeps the old one. Use when a reader could mistake an example for a result.

  • learning-loop

    Turns mistakes and wins into improvements: observe, diagnose, propose, test, promote, check. A rule needs evidence, a test, a contrary case and authority; one case is weak evidence, so name where the rule would be wrong. Use before adding any rule.

  • maturity-check

    Places a person on Yegge's eight AI-development levels and a team on n8n's five maturity levels, scoring evidence separately from self-report, then names the SHOTos stage and skills to start with. Use when asked "where am I with AI" or before granting autonomy.

  • pilot-before-scale

    Pilots three or fewer items before a run of more than three, then completes a preflight checklist before the full run. Use for bulk edits, mass drafts, clean-ups, migrations or any run touching many records.

  • progress-wrap-up

    Writes the weekly progress wrap-up on an evidence ledger, classing each claimed win as live, gated, merged only or unverified, and ending with asks. Use when reporting weekly progress to a sponsor or team. Final results go to evidence-pack.

  • report-with-evidence

    Ends a task that changed something with a short report and Claims block: what was done, how to check it, what was only planned or unchecked. Use when saying something is done, fixed, sent, deployed or passing.

  • research-and-assemble

    Researches from sources, keeps each fact with its source, separates fact, inference and guess, and checks every claim before handover. Use when building briefings, comparisons, reports or proposals from outside material that others will rely on.

  • resume-pack

    Writes a resume pack when a session ends or context fills: handoff note, exact next prompt, pending manual steps and learnings, with no secrets or raw conversation. Use when pausing unfinished work for another session. Use evidence-handoff when a new owner needs to take over.

  • retrospective

    Runs a short blameless retrospective: what we expected, what happened, why, and what we change, with an owner and date each. Use when a pilot, release, incident or project phase ends, or after a surprise. Not for appraising people.

  • rollout-plan

    Plans taking something that worked to more teams: a first wave of three or fewer, what is reused, what each team re-baselines, governance. Use when a scale decision is made, even if asked to go everywhere at once. A draft until the sponsor agrees.

  • route-the-work

    Writes a one-line route (asset, job, risk, reader, route, proof) and chooses who does the work: direct, a skill, a role agent or a reviewer. Use when starting any task others will rely on.

  • runbook

    Writes a runbook from what was actually done: owner, steps, checks, failure handling and rollback, so a team that did not build it can run it. Use when a process becomes someone else's job or depends on one person's memory.

  • skill-quality-gate

    Runs a quality gate before promoting a skill or change: one change, one comparison, three scenarios, a maturity label and a disclosure checklist. Use when changing, promoting or publishing any skill, prompt, template or agent instruction.

  • stakeholder-map

    Maps who is affected by a piece of work, who decides and who can block it, with goal, influence, stance and labelled links. Use when starting a change, project or deal. Roles only, not private profiles.

Subagents (10)

  • README
  • business-analyst

    Turns a request into scope, an owner and acceptance examples before any work starts. Use at the start of a task when "done" is not yet defined, when a request is vague, or when several people want different things. Never builds.

  • data-steward

    Classifies the data a task touches and checks consent, purpose and exposure, with particular care for children's data and special-category data. Read-only. Use before a task reads, copies, shares or publishes personal data, and before any dataset leaves its home.

  • enablement-coach

    Writes runbooks, guides and capability matrices so a team can run a piece of work without the person who built it. Use when a process works but only one person knows how, or when a team is adopting a new way of working.

  • engineer

    Builds the smallest vertical slice that meets an agreed acceptance card, writes the check first where practical, and reads the result back in its real home. Use for implementation work once scope and acceptance are agreed.

  • qa-lead

    Verifies finished work against the acceptance card with evidence. Read-only apart from running tests and checks. Use after the engineer or writer says the work is done and before anyone asks the owner to accept it.

  • release-manager

    Prepares a frozen approval manifest and checklist for anything that is going out: a send, a publish, a deploy, a spend or a delete. Never executes without the owner's yes. Use when reviewed work is ready to leave the project.

  • sceptic-reviewer

    Pressure-tests a plan, claim or finished result and finds the cheapest way it fails. Read-only. Use before committing to a plan, before a claim goes to a customer or board, and when everyone agrees too quickly.

  • security-reviewer

    Reviews a change or plan for secrets, permissions, data exposure and trust boundaries. Read-only. Use before anything merges, ships or connects to an outside system, and whenever a task touches credentials, access or personal data.

  • ux-designer

    Describes the user flow and the shape of a screen, form, message or document before anyone builds it, and checks accessibility. Use after acceptance is agreed and before engineering starts on anything a person will read, click or fill in.

Hooks (1)

  • Stop

    sh "${CLAUDE_PLUGIN_ROOT}/hooks/run_hook.sh"

View source on GitHub

More from SHOTClubhouse/shotos

All 13 plugins →

SHOTos pack for winning work: the LEAP pipeline, NUDGE qualification, relationship maps, contextual proposals, proposal factories, outbound prospecting and email replies. Drafts by default; sends only after a yes on exactly what goes.

10 skills

1

Eight skills for papers, slide decks, explainers, press releases, demo videos, creator edits, campaign websites and small websites. Every fact is sourced and nothing is published without a yes.

8 skills

1

Operating-week skills for founders and executives working with an agent: a pull-based daily brief, a leader's inbox, mail triage, meeting notes, weekly briefing, decision briefs and advisory sessions. Drafts by default; sends only after a yes on exactly what goes.

7 skills

1

Social media skills for working with an agent, for any brand, club, creator or small business: set up an account, plan a week, write caption options, publish only through a frozen approval manifest, review engagement, share into groups and review monthly insights. Drafts first; a person approves.

7 skills

1

SHOTos pack for founder admin: grant and award finding, investor updates, due-diligence data rooms and advisory board setup. Drafts by default; submits, pays or shares only after a yes on exactly what goes.

5 skills

1

Keep files findable and safe, for people and agents: a work folder, file naming, filing with de-duplication, and a quarantine for doubtful files.

5 skills

1

Maintain shotos-core?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins13 plugins