cann-workbench 0.0.0-stage → 0.0.2-alpha

package/skills/mattpocock/skills/in-progress/software-factory/RUNNERS.md

@@ -0,0 +1,94 @@
+# Runners
+
+> Surveyed 2026-10, and not guaranteed to be up to date. Use it to get oriented, then research the current options yourself: products, prices, limits and betas change fast.
+
+A runner is **disposable**: every run starts on a fresh machine and leaves nothing behind. Five types fill the slot. They differ mostly in who owns the agent loop and who owns the machine:
+
+| Type | Agent loop | Machine | Also fills |
+| --- | --- | --- | --- |
+| CI runner | yours, inside the CI job | CI vendor's, or yours | orchestrator, observability platform |
+| MicroVM API | yours, in the orchestrator or on the runner | provider's | nothing |
+| Bundled agent platform | vendor's | vendor's | part of orchestrator, observability platform |
+| Bring-your-own worker | vendor's | yours | part of orchestrator, observability platform |
+| Own VPS or containers | yours | yours | nothing |
+
+Runner choice is per run: a cheap CI runner for review runs and a microVM for implementer runs is a normal design.
+
+## CI runners
+
+A fresh VM or pod per CI job, started by the git host's own workflow engine; the agent CLI is one step in the job. The orchestrator starts a run with a workflow trigger (issue, PR, schedule, manual dispatch), and a concurrency group keeps two runs off the same ticket. Hosted runners are disposable by construction; self-hosted runners get there through an ephemeral mode, one pod per job, deleted after. Cost is per minute.
+
+**Pick it when** the git host is GitHub or GitLab and every trigger is a git host event or a clock: the workflow file is the orchestrator and the run page is the observability platform, so one product fills three slots.
+
+Starting points:
+- [GitHub Actions](https://docs.github.com/en/actions/reference/limits): the default for an all-GitHub factory; [pricing](https://docs.github.com/en/billing/reference/actions-runner-pricing).
+- [Claude Code GitHub Action](https://code.claude.com/docs/en/github-actions): Claude Code as a workflow step.
+- [GitLab hosted runners](https://docs.gitlab.com/ci/runners/hosted_runners/linux/): an ephemeral VM per job.
+- [Actions Runner Controller](https://docs.github.com/en/actions/concepts/runners/actions-runner-controller): self-hosted, one ephemeral pod per job on the user's Kubernetes.
+
+## MicroVM APIs
+
+An SDK call creates an isolated microVM (vendors say "sandbox") in about a second; the orchestrator execs commands into it, or starts an agent CLI inside it. Cost is per second of vCPU and RAM. The orchestrator creates one per run, kills it at the end, and sets a timeout as the backstop. Providers also sell persistence (pause/resume, snapshots, drives); a factory uses it as a cache, and keeps memory between runs in the ticket tracker, git host and orchestrator.
+
+**Pick it when** the factory has its own orchestrator (a server, a queue) and wants many short-lived, parallel runs with no machines to manage. Compare on max run length, concurrency cap, and whether time spent waiting on the model is billed: as of 2026-10, Vercel bills only active CPU, so model-wait time is nearly free there.
+
+Starting points: [E2B](https://e2b.dev/pricing), [Daytona](https://www.daytona.io/pricing), [Modal Sandboxes](https://modal.com/docs/guide/sandboxes), [Vercel Sandbox](https://vercel.com/docs/vercel-sandbox/pricing).
+
+## Bundled agent platforms
+
+A hosted coding agent with its runner included: the vendor provisions a fresh VM or container per run, runs its own agent loop there, and pushes a branch or PR. Only the branch survives. Runs start from an @-mention or assignment in the git host or ticket tracker, a chat message, a schedule, or an HTTP call, so the platform fills much of the orchestrator; its transcript view fills the observability platform. Cost is folded into a seat or subscription, or charged per run.
+
+**Pick it when** the user wants the fewest moving parts and is happy with that vendor's agent. Confirm its triggers cover the user's ticket tracker.
+
+Starting points:
+- [Claude Code cloud](https://code.claude.com/docs/en/claude-code-on-the-web), with [scheduled tasks](https://code.claude.com/docs/en/routines) for cron, API and GitHub event triggers.
+- [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview): API-first; create a run against an environment and stream events.
+- [Codex cloud](https://developers.openai.com/codex/cloud): a container per task.
+- [Copilot coding agent](https://docs.github.com/en/copilot/concepts/agents/coding-agent/about-coding-agent): assign an issue to Copilot; its runner is a GitHub Actions runner.
+
+## Bring-your-own worker
+
+The bundled platform keeps its agent loop and its queue of runs, but tool calls execute on a worker the user hosts. The worker polls the vendor outbound, claims a run, executes it, and exits: the same shape as a self-hosted CI runner. Disposability is the user's job: run the worker under Kubernetes or a microVM API so each run gets a fresh disk. Cost is the vendor's seat or usage plus the user's machines.
+
+**Pick it when** the user wants a bundled agent but runs must reach a private network, keep data on the user's machines, or use custom hardware.
+
+Starting points: [Claude Code self-hosted environments](https://code.claude.com/docs/en/self-hosted-environments), [Cursor self-hosted pool](https://cursor.com/docs/cloud-agent/self-hosted-pool), [Copilot coding agent on ARC](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/coding-agent/customize-the-agent-environment).
+
+## Own VPS or containers
+
+A machine the user rents or runs, with a fresh container (or machine) per run: the machine may live for months, the container lives for one run. Max run length is whatever deadline the orchestrator sets. Disposability comes from `docker run --rm`, a Kubernetes Job with `ttlSecondsAfterFinished: 0`, or a machine destroyed at the end; every cache sits on a path the next run treats as optional. Cost is flat monthly, or per second while running.
+
+**Pick it when** runs are long, steady or heavy, cost per hour dominates, or a server already hosts the orchestrator.
+
+Starting points: [Fly Machines](https://docs.fly.io/machines/overview) ([pricing](https://docs.fly.io/about/pricing)), [Hetzner Cloud](https://www.hetzner.com/cloud/) plus Docker, [Kubernetes Jobs](https://kubernetes.io/docs/concepts/workloads/controllers/job/).
+
+## Researching further
+
+### The questions that decide the slot
+
+Check each candidate against these, with the factory's runs in hand:
+
+1. **How does the orchestrator start one?** A workflow trigger, an SDK call, an @-mention, an HTTP call, or a vendor queue that a worker claims. Does that fit the orchestrator the design already names?
+2. **What is the max run length, and the concurrency cap?** Find both the default timeout and the ceiling, per plan tier, and what happens at the cap. Hold them against the design's longest run and busiest burst.
+3. **What is the cost shape?** Per minute, per second of vCPU and RAM, active CPU only, per run, per seat, or flat monthly. Is time waiting on the model billed? Are model tokens inside the price or on top?
+4. **How is disposability achieved?** Fresh by default, an ephemeral flag, or the orchestrator's own teardown. Which persistence features exist, and can the design keep them to caches?
+5. **What can a run reach?** Private network access, outbound firewall or allowlist, how secrets reach the runner, and who else can read them.
+6. **Which other slots does it fill?** Count the triggers it reads as orchestrator coverage, and its run page or transcript as observability platform coverage.
+
+### Where the answers live
+
+- The vendor's **limits or quotas page** and **pricing page**, over the landing page.
+- The **SDK or API reference** for the create call: its timeout, lifecycle and network parameters.
+- The **security or networking docs** for firewalls, allowlists and secret handling.
+- The **changelog or release notes** for beta, preview and GA status, and for plan gating (Team, Enterprise).
+- For CI runners, the git host's **billing docs**.
+
+### What goes stale fastest
+
+- **Prices and free allowances.** As of 2026-10, GitHub had announced a per-minute fee for self-hosted runners, then postponed it.
+- **Beta, preview and early-access status**, and which plans unlock a feature. As of 2026-10, Claude Managed Agents and Claude Code self-hosted environments were both in beta.
+- **Default timeouts and max run length** per tier.
+- **Trigger integrations** on bundled platforms: which ticket trackers and chat tools start a run.
+- **Startup times**, which are vendor claims; measure them if they matter.
+
+The type traits above (who owns the loop, who owns the machine, which slots it fills) change slowly; trust them over any number here.

package/skills/mattpocock/skills/in-progress/software-factory/SKILL.md

@@ -0,0 +1,98 @@
+---
+name: software-factory
+description: Shared language for designing a software factory: the tasks it runs and the services it plugs into.
+disable-model-invocation: true
+---
+
+A **software factory** is a system of agents that turns tickets, PRs and schedules into merged code, deployed on remote infrastructure the user chooses. This skill is the language for designing one. Use these terms, and only these, when discussing or whiteboarding a factory; when the user reaches for a word under _Avoid_, name the canonical term.
+
+## Tasks and runs
+
+**Task**:
+A kind of work the factory performs, defined once and run many times: review, explore, implement, ratchet. A task may work on a ticket, a PR, or the codebase as a whole.
+_Avoid_: job, workflow, action
+
+**Trigger**:
+The event that starts a run: a change in the ticket tracker or git host, a clock in the orchestrator, or another run.
+
+**Run**:
+One execution of a task on one runner, from its trigger to its finish, treated as a black box. A run triggers further runs either directly, through logic in the orchestrator, or by changing the ticket tracker or git host. A run never waits for a human: it ends, and the human's later change to the ticket tracker or git host triggers a new run.
+_Avoid_: session
+
+**Runner**:
+The disposable machine a run executes on. Nothing on it survives the run, even when the machine itself is long-lived: a run's only memory of earlier runs is the ticket tracker, the git host and the orchestrator.
+_Avoid_: server, host, box, compute, sandbox
+
+## Services
+
+**Ticket tracker**:
+Where tickets live, and the factory's human interface: humans schedule work by filing tickets, talk to agents in their comments, and their changes to tickets trigger runs.
+_Avoid_: issue tracker, ticket manager, project board
+
+**Ticket source**:
+Anything outside the factory that creates tickets in the ticket tracker: a feedback button, a monitor, an error tracker, an inbox.
+_Avoid_: data source, trigger source, intake
+
+**Git host**:
+Where branches, PRs and reviews live.
+_Avoid_: code host, forge, repo
+
+**Orchestrator**:
+The component that receives triggers, starts runs on runners, and records which runs are queued, in flight or finished.
+_Avoid_: dispatcher, scheduler, control plane
+
+**Observability platform**:
+Where runners send logs, traces and status, so a human can see what happened inside each run. Optional: the product filling the runner or orchestrator slot often shows enough on its own. A run never decides on it until something writes it into the ticket tracker or git host.
+_Avoid_: observability, logs, monitoring, dashboard
+
+## Designing a factory
+
+A design has two halves: the **services**, each a slot filled with a product, and the **tasks** whose runs move work through them.
+
+Start from the user's problem, not the factory: untriaged tickets, PRs waiting for automated review, a stricter automated check to migrate to, bugs nobody reads. When the user names a problem or doesn't know what to build, read [EXAMPLE-TASKS.md](EXAMPLE-TASKS.md) for the tasks that solve common ones.
+
+### Start slow
+
+Every trigger is an accelerator. Accelerators without brakes make a slop cannon. There are three brakes:
+
+- **Automated checks**: deterministic gates (types, lint, tests) that every run must pass.
+- **Automated review**: a separate run that reads the diff cold against the codebase's standards and the ticket, when there is one.
+- **Human review**: a human reads the PR before it merges; what it catches becomes new automated checks and sharper automated review.
+
+Add one automated trigger at a time, throttled at first (one bug report in ten, a clock once a day), with human review on every PR. Open the throttle as the brakes earn trust, and cap every loop of runs at a few tries before a human.
+
+### Fill every slot
+
+Each service is a slot. One product can fill several slots, and one server can host several services. Three designs, side by side:
+
+| Service                | All on GitHub                   | Linear tickets                 | Own tracker              |
+| ---------------------- | ------------------------------- | ------------------------------ | ------------------------ |
+| Ticket tracker         | GitHub Issues                   | Linear                         | own app                  |
+| Ticket source          | feedback button                 | feedback button, monitor       | feedback button, monitor |
+| Git host               | GitHub                          | GitHub                         | GitHub                   |
+| Orchestrator           | GitHub Actions                  | own server + database          | own app                  |
+| Runner                 | Actions runner                  | Actions, E2B, Daytona or a VPS | own app, or sandboxes    |
+| Observability platform | none: Actions run pages suffice | an LLM tracing platform        | own app                  |
+
+When the user is choosing a product for a slot, read that slot's survey to get oriented, then research the current options yourself; each survey groups the options by type and lists the questions that decide the slot:
+
+- [TICKET-TRACKERS.md](TICKET-TRACKERS.md)
+- [GIT-HOSTS.md](GIT-HOSTS.md)
+- [RUNNERS.md](RUNNERS.md)
+- [OBSERVABILITY-PLATFORMS.md](OBSERVABILITY-PLATFORMS.md)
+
+Buy the services and build the tasks: the tasks carry the user's design, the services are generic. Favour an off-the-shelf ticket tracker: it is robust, people already know it, and outside users are easy to let in.
+
+### Question every task
+
+For each task, answer:
+
+1. What triggers it?
+2. What does it do, and which services does it read and write?
+3. What does it trigger next?
+4. Where does a human re-enter?
+5. What stops two runs doing the same work?
+
+For each ticket source, answer: what stops it filing the same ticket twice?
+
+A design is finished when every slot names a product (or, for the observability platform, a deliberate none) and every task and ticket source has an answer to every question.

package/skills/mattpocock/skills/in-progress/software-factory/TICKET-TRACKERS.md

@@ -0,0 +1,85 @@
+# Ticket trackers
+
+> Surveyed 2026-10, and not guaranteed to be up to date. Use it to get oriented, then research the current options yourself: products, prices, limits and betas change fast.
+
+The ticket tracker is the factory's human interface. Each type below is a starting point: read what it is and when a factory picks it, then check the examples against the questions in [Researching further](#researching-further).
+
+## The types
+
+### 1. Git-host tracker
+
+The tracker built into the git host, so tickets, branches and PRs share one product, one permission model and one identity. A factory picks it when it is small, the team already lives on the git host, or the repo is public. This is the "All on GitHub" design: the git host's CI fills the orchestrator slot with no glue. Labels are the dependable router, because statuses live on a separate board. Outside developers file where the code is; non-developers need an account, so a feedback button files through the API. Self-hosted git hosts carry their tracker with them.
+
+- [GitHub Issues](https://docs.github.com/en/copilot/concepts/agents/about-third-party-agents): the default; assign-to-agent for Copilot, Claude and Codex.
+- [GitLab Issues](https://about.gitlab.com/blog/how-to-use-a-work-item-created-trigger/): Duo Agent Platform flows triggered from work items.
+- [Forgejo](https://forgejo.org/2026-10-release-v17-0/): self-hosted, Actions-compatible.
+
+To verify: which assign-to-agent features are still in preview and which plans include them; whether a native agent reads later comments or only the ticket at assignment (as of 2026-10, Copilot reads it at assignment only).
+
+### 2. Agent-native dev tracker
+
+A standalone SaaS tracker for software teams that treats agents as first-class assignees, with an agent API and its own coding agent. A factory picks it when product, support or design staff schedule work, the team already lives there, or it wants polished triage and planning views. The "Linear tickets" design. Statuses and workflows are first-class, so "moved to Ready" is a clean trigger. Agents appear as app users a human delegates to, and runs can stream progress into the ticket. Native agents here are the deepest of any type, so one can partly fill the orchestrator and runner slots too.
+
+- [Linear](https://linear.app/developers/agents): the most agent-shaped tracker.
+- [Jira](https://support.atlassian.com/jira-software-cloud/docs/collaborate-on-work-items-with-ai-agents/): status-triggered agents; fits an org already on Atlassian.
+- [Shortcut](https://www.shortcut.com/help/integrations/using-ai-agents): assign a story or mention an agent in a comment.
+- [YouTrack](https://www.jetbrains.com/youtrack/): workflows-as-code; self-hosts.
+
+To verify: agent API status (Linear's was a developer preview as of 2026-10); how native agent runs are metered and priced; agent seat cost; acknowledgement deadlines on agent webhooks; which plan unlocks customer-facing forms; self-hosted edition end-of-life dates.
+
+### 3. Open-source dev tracker
+
+A Linear-style tracker you can run on your own infrastructure, with a cloud edition beside it. A factory picks it when data stays in-house (air-gapped, regulated) or the user wants to read and patch the tracker's source while still buying it. Routing by states, labels and custom properties works much as in type 2; native agents are younger.
+
+- [Plane](https://developers.plane.so/dev-tools/agents/overview): Linear-like; bot users per app; agents reply in comments.
+- [Huly](https://github.com/hcengineering/huly-selfhost): all-in-one workspace with two-way GitHub sync; a heavy stack to operate.
+- [OpenProject](https://www.openproject.org/): mature, classic project management.
+
+To verify: agent feature status (Plane's was beta as of 2026-10); which edition carries guest roles and intake forms; licence; the self-hosted stack's operating cost.
+
+### 4. General work tool
+
+A work-management or docs tool whose database or task list doubles as the tracker. A factory picks it when it serves a non-engineering team already living there, or tickets are mostly content, ops or research rather than code. Forms are the strength: anyone with a link files a ticket. Routing is flexible database properties, so every factory invents its own schema. Developer context (diffs, PRs) sits a click away on the git host. SaaS only.
+
+- [Notion](https://www.notion.com/help/custom-agents): database-as-tracker; agents fire on database changes.
+- [Asana](https://asana.com/product/ai/ai-teammates): AI Teammates take assigned tasks.
+- [ClickUp](https://clickup.com/brain/cloud-agents): Cloud Agents return a PR in the task thread.
+- [Trello](https://developer.atlassian.com/cloud/trello/guides/rest-api/webhooks/): boards and lists; webhooks plus Butler automation.
+
+To verify: webhook latency and granularity (as of 2026-10, Notion batched content updates, arriving a minute or two late); which plan includes agents.
+
+### 5. Repo-native tracker
+
+Tickets stored as files in the repo (JSONL, Markdown), edited by agents through a CLI or MCP server and merged like code. A factory picks it when one developer drives agents locally and wants the plan in git, or as a run's working memory beside a real tracker. A push to the git host is the only trigger, so the orchestrator diffs files to find what changed. Identity is the git host's. Outside filing is a commit or PR, the weakest of any type, so a factory graduates to a git-host tracker once others file tickets.
+
+- [Beads](https://github.com/steveyegge/beads): JSONL with dependency tracking, so a run picks the next unblocked ticket.
+- [Backlog.md](https://github.com/MrLesk/Backlog.md): Markdown tasks with a Kanban view and MCP server.
+
+### 6. Build-your-own
+
+The factory's own app holds tickets in its own database, usually beside the orchestrator. The "Own tracker" design. A factory picks it when the tracker *is* the product (an internal platform, a customer-facing support factory) or no off-the-shelf model fits. Triggers become function calls; every trait in the questions below becomes code to write and maintain, which is why the skill favours buying. An [Airtable](https://airtable.com/developers/web/api/webhooks-overview) base with webhooks is a half-built middle.
+
+## Researching further
+
+Check each candidate against these questions. They decide the slot:
+
+- **Triggers**: which ticket changes (created, labelled, status moved, assigned, commented, mentioned) emit a webhook or event the orchestrator can turn into a run? How fast and how granular?
+- **Routing**: which labels, statuses or fields can a run read to know its kind (explore, implement, rework)?
+- **Thread**: can a human answer an agent in comments, and does that reply trigger the next run?
+- **Identity**: is there an API plus a bot identity, so runs act as themselves and humans tell agent from colleague? Does the bot cost a seat?
+- **Native agents**: can a ticket be assigned to an agent directly? Which agents, on which plan, metered how? What does it read: the ticket at assignment, or the whole thread?
+- **Outside filing**: how does a ticket source or customer create tickets: forms, email, chat, API? Which plan unlocks it?
+- **Hosting**: SaaS only, or self-hosted, and under which licence?
+
+Answers live in primary sources: the API and webhook reference (event lists, payloads, delivery and retry rules), the agent or app developer docs, the pricing page and plan comparison table, and the changelog or release notes. Prefer these over blog posts and comparison sites.
+
+Stalest first: agent features and their preview or beta status, agent metering and credit prices, plan gating of agents and forms, rate limits, and acquisitions, shutdowns and end-of-life dates for self-hosted editions. Webhook event lists and routing models change slowly.
+
+## Durable gotchas
+
+Verify each still holds before relying on it:
+
+- **GitHub's `GITHUB_TOKEN` trap**: changes made with the default `GITHUB_TOKEN` trigger no new workflow runs. A run that labels or comments on a ticket to trigger the next run acts through a GitHub App token.
+- **Assignment-time context**: some native agents read the ticket only when assigned, so later context goes on the PR.
+- **Agent webhooks expect a fast acknowledgement**: the orchestrator acknowledges at once and starts the run afterwards.
+- **Batched webhooks in general work tools** arrive late; a factory needing prompt runs triggers on property changes or picks another type.

package/skills/mattpocock/skills/in-progress/writing-beats/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: writing-beats
+description: Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
+disable-model-invocation: true
+---
+
+<what-to-do>
+
+The user has passed (or will pass) a markdown file of raw material. This is **exploit**: the exploring is done, the pile is fixed. Commit to a path through it and mine the pile to fill each beat.
+
+If the user did not say where to save the article, ask once and remember the path.
+
+Then run a beat-by-beat journey, choose-your-own-adventure style:
+
+1. **Establish the prerequisites.** Before any beats, settle with the user what the audience already knows walking in: the concepts that are **grounded** from the start. Everything else must be grounded by a beat before a later beat can use it. See [Grounding](#grounding).
+2. Write 2–3 candidate **starting beats**, drawn from the raw material. Each is a different entry point into the article. Each may only lean on grounded concepts; note what new concepts each one grounds. Show the user the beats before writing to the article file. The user picks one. Preview what beats that pick unlocks, as if the user is seeing a little way down the path.
+3. Once the user picks a starting beat, write **only that beat** to the article file. A beat may be one sentence or several paragraphs, whatever that beat naturally is. Stop there.
+4. Re-read the article file from disk. Then offer 2–3 candidate **next beats**: different directions the journey could pivot to from where the article now stands. Each must be reachable from the current grounded set; note what each one grounds.
+5. Loop steps 3–5 until the article reaches a natural end.
+
+</what-to-do>
+
+<supporting-info>
+
+## Grounding
+
+Every **concept** has to be **grounded** before a beat can lean on it: the audience either walked in knowing it or met it in an earlier beat. A beat that reaches for an ungrounded concept loses the reader; that is the one move the journey can't make. The unit is the concept, not the word for it: a beat can lean on an idea the reader lacks even with no jargon in sight. Where a concept has a name (a **term**), grounding it means landing the idea and the term together.
+
+A concept gets grounded one of two ways:
+
+- **Prerequisite**: grounded before the first beat. The audience brings it. Fixed at the start.
+- **Introduced**: a beat establishes it, and from then on it's grounded for every later beat.
+
+So each beat does two jobs: it **requires** concepts that are already grounded, and it **grounds** new ones. Keep a running list of what's grounded so far, and update it each time a beat lands.
+
+This is what shapes the choose-your-own-adventure. A candidate beat is only reachable if everything it requires is already grounded; picking a beat that grounds concept X unlocks every beat that was waiting on X. When you offer next beats, they must all be reachable from the current grounded set, and say what each one grounds, so the user can see which paths it opens.
+
+The big lever is what you make a prerequisite versus what you ground inside the piece. Demand too much up front and you shut out readers who don't have it; ground too much inside and the early beats drown in definitions. Settle this with the user when you establish prerequisites, and revisit it whenever a tempting beat turns out to require a concept nothing has grounded yet: the fix is either a grounding beat before it, or promoting the concept to a prerequisite.
+
+## What is a beat
+
+A beat is one move in the journey. It does one thing: sets a scene, lands a point, asks a question, drops an aside, twists the angle. Then it stops, leaving the reader at a place where the next beat can pivot.
+
+A beat is sized by what it needs:
+
+- A single sentence if that's all the move is ("And then nothing happened for three weeks.").
+- A short paragraph if the move needs setup.
+- Multiple paragraphs if the beat is a self-contained vignette, argument, or example.
+
+If a "beat" needs five paragraphs and three subheadings, it's not a beat; it's two beats glued together. Split it.
+
+## Pulling from the pile
+
+Pull material from the raw pile to populate each beat. You can paraphrase, split, recombine, or quote. The pile is a quarry.
+
+## Ending the journey
+
+The article ends when the journey is complete, not when the pile is empty. Most piles will have leftover fragments that don't make it in. That is fine; that is the point of having more raw material than you need.
+
+## Writing rhythm
+
+- Append one beat at a time. Never write ahead.
+- Re-read the article file from disk before every write. Preserve user edits absolutely.
+- If the user edits a previous beat substantially, let it change what comes next.
+- If the user says "rewrite that beat" or "go back and try a different beat 3", do it: edit in place, leave the rest alone.
+
+</supporting-info>

package/skills/mattpocock/skills/in-progress/writing-beats/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Writing Beats"
+  short_description: "Assemble raw material into beats"
+policy:
+  allow_implicit_invocation: false

package/skills/mattpocock/skills/in-progress/writing-fragments/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: writing-fragments
+description: "Writing, explore: mine raw fragments, no structure yet."
+disable-model-invocation: true
+---
+
+<what-to-do>
+
+This is pure **explore**: widen the space of what could be written without committing to structure. Committing is _exploit_, a separate skill's job. Run a grilling session that produces fragments, interviewing the user relentlessly about whatever they want to write about. Imposing phases, outlines, or article structure is out of scope here.
+
+As fragments emerge from either side of the conversation, append them to a single markdown file.
+
+If the user did not pass a path, ask once where to save the document, then remember it for the rest of the session.
+
+Capture fragments from the very first thing the user says, including the initial prompt.
+
+On first write, put a single H1 at the top with a working title (it can change later) and nothing else: no metadata, no TOC, no date.
+
+</what-to-do>
+
+<supporting-info>
+
+## What is a fragment
+
+A fragment is any piece of text that might survive into the final article. It must be _readable by the author_ (the author can tell what it means), but it does not need to define its terms or be comprehensible to a cold reader. The bar is "is this a piece of good writing?", not "is this a self-contained argument?"
+
+Fragments are deliberately heterogeneous. Examples of what could be a fragment:
+
+- A sharp sentence you'd want to deploy somewhere but don't yet know where.
+- A claim with a one-line justification.
+- A vignette: a thing that happened, a code snippet, a scenario, an analogy.
+- A half-thought: "something about how X feels like Y, work this out later."
+- A quote, a piece of dialogue, an overheard line.
+- A list of related observations that hang together by feel.
+- A complaint, a confession, a punchline.
+- A **leading word**: a compact metaphor or coinage the whole piece can hang on (one term that names the idea, the way _tracer bullets_ or _fog of war_ names a whole pattern).
+
+Of these, the leading word is the most valuable fragment to land. It is load-bearing: name the right one in explore and it shapes the structure, the transitions, and the title later, paying dividends through the entire exploit phase. When the conversation circles a recurring idea, push to coin a word for it.
+
+The novelist's diary is the model: years of unstructured noticings that later get mined for raw material. Fragments are noticings.
+
+## File format
+
+```markdown
+# Working title
+
+A first fragment lives here.
+
+It can be multiple paragraphs. It can include lists, code, quotes: whatever
+shape the fragment naturally takes.
+
+---
+
+A second fragment.
+
+---
+
+> A quoted line that the user wants to keep around.
+
+A reaction to it.
+
+---
+
+- A cluster of related observations
+- That hang together by feel
+- And want to be near each other
+```
+
+Fragments are separated by a horizontal rule (`\n---\n`). No headings inside the body. No tags. No order beyond the order they were added.
+
+## Writing rhythm
+
+Append silently. Don't ask permission for each fragment. Mention what you added in passing ("adding that"), but don't interrupt the conversation with save dialogs.
+
+Before every write: re-read the file from disk. The user may have edited, reordered, or deleted fragments between turns, so preserve their changes. Never overwrite the file; only append (or, if the user asks, edit a specific fragment in place).
+
+The user can say "cut the last one", "rewrite that one sharper", "merge those two" at any time. Treat those as first-class instructions.
+
+</supporting-info>

package/skills/mattpocock/skills/in-progress/writing-fragments/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Writing Fragments"
+  short_description: "Mine raw writing fragments"
+policy:
+  allow_implicit_invocation: false

package/skills/mattpocock/skills/in-progress/writing-shape/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: writing-shape
+description: "Writing, exploit: shape raw material into an article, paragraph by paragraph."
+disable-model-invocation: true
+---
+
+<what-to-do>
+
+The user has passed (or will pass) a markdown file of raw material. Treat it as the input pile: anything from a tidy list of fragments to a wall of unstructured prose to a transcript. The format does not matter. Read it end-to-end before doing anything else.
+
+Then run a shaping session that produces a separate article document. This is **exploit**: the exploring is done, the pile is fixed: commit to a structure and mine the pile to fill it. Do not edit the raw material file: it is read-only to this skill.
+
+If the user did not say where to save the article, ask once and remember the path.
+
+</what-to-do>
+
+<supporting-info>
+
+## The loop
+
+1. **Read the pile.** Read the input file in full. Form a sense of what's in it.
+2. **Establish the prerequisites.** Settle with the user what the reader knows walking in: the concepts that are **grounded** from the start. Everything else must be grounded by a block before a later block can lean on it. See [Grounding](#grounding).
+3. **Draft 2–3 candidate openings.** Each opening should imply a different thesis or angle for the article. Show all of them. Force the user to pick or compose a hybrid. The chosen opening defines what the rest of the article must do.
+4. **Grow paragraph by paragraph.** After the opening lands, ask "given this opening, what does the reader need to hear next?" Pull material from the pile to answer. The next block may only lean on grounded concepts, and grounds new ones as it lands. Argue about the form the next block takes: a paragraph, a list, a table, a callout, a quote, a code block. Each format choice should be deliberate and defensible.
+5. **Append to the article file as you go.** Don't batch. Write each agreed paragraph or block immediately so the user can see the article taking shape.
+6. **Loop step 4 until the article is done.** The user decides when it's done.
+
+## Grounding
+
+Every **concept** has to be **grounded** before a block can lean on it: the reader either walked in knowing it or met it in an earlier block. A block that reaches for an ungrounded concept loses the reader. The unit is the concept, not the word for it: a block can lean on an idea the reader lacks even with no jargon in sight. Where a concept has a name (a **term**), grounding it means landing the idea and the term together.
+
+A concept gets grounded one of two ways:
+
+- **Prerequisite**: grounded before the opening. The reader brings it. Fixed at the start.
+- **Introduced**: a block establishes it, and from then on it's grounded for the rest of the article.
+
+Keep a running list of what's grounded. When you ask "what does the reader need to hear next?", an ungrounded concept the next move needs is itself the answer: ground it first (here or in an earlier block) or you can't make the move. This is the gap-naming of [Pulling from the pile](#pulling-from-the-pile) one level up: there the pile is missing material; here the article is missing a foundation.
+
+The lever is what you make a prerequisite versus what you ground inside the article. Demand too much up front and you shut readers out; ground too much inside and the opening drowns in definitions. Settle it with the user when you establish prerequisites.
+
+## Conversational feel
+
+This is a grilling session inverted. In ideation, the question was "what are you actually noticing?" Here it's "what is this article actually arguing, and in what order does the reader need to hear it?" Push back. Refuse to let weak transitions slide. If a paragraph doesn't earn its place, cut it.
+
+Specific moves to keep using:
+
+- "What does this paragraph do for the reader that the previous one didn't?"
+- "If I cut this, what breaks?"
+- "Is this prose, or should it be a list? Why prose?"
+- "This sentence is doing two jobs: split it or pick one."
+- "The opening promised X. We've drifted to Y. Either re-thread it or change the opening."
+
+## Pulling from the pile
+
+Treat the raw material as a quarry, not a script. Pull a fragment, rework it to fit the surrounding paragraph, and place it. A fragment may be split across multiple paragraphs, merged with another, or paraphrased. The pile's job is to be mined; the article's job is to read as one voice.
+
+If the pile lacks something the article needs, name the gap explicitly: "We need an example here and the pile doesn't have one. Give me one now or we cut this section."
+
+## Format arguments to actually have
+
+When choosing how to render a block, weigh these tradeoffs out loud with the user, not silently:
+
+- **Prose vs. list.** Prose carries argument; lists carry parallel items. If items aren't truly parallel, prose is better. If they are, a list is faster to scan.
+- **Inline vs. callout.** Tips, warnings, and asides go in callouts (`> [!TIP]`, `> [!NOTE]`), but only if they'd genuinely derail the main argument inline. Otherwise leave them inline.
+- **Table vs. repeated structure.** If the same shape repeats 3+ times with the same fields, a table. Otherwise prose with bold leads.
+- **Quote vs. paraphrase.** Quote when the original wording is the point. Paraphrase when only the idea matters.
+- **Code block vs. inline code.** Multi-line, runnable, or illustrative → block. Single token or identifier → inline.
+
+## Writing rhythm
+
+Append to the article file as each block is agreed. Re-read the file from disk before every write: the user may have edited between turns. Never overwrite blindly. If the user wants a paragraph rewritten, edit that specific paragraph in place; leave the rest alone.
+
+## Out of scope
+
+- Mining for new fragments that aren't in the pile (handle gaps as in "Pulling from the pile").
+- Editing the raw material file.
+- Publishing, formatting for a specific platform, or adding frontmatter the user didn't ask for.
+
+</supporting-info>

package/skills/mattpocock/skills/in-progress/writing-shape/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Writing Shape"
+  short_description: "Shape raw material into an article"
+policy:
+  allow_implicit_invocation: false

package/skills/mattpocock/skills/misc/README.md

@@ -0,0 +1,8 @@
+# Misc
+
+Tools I keep around but rarely use, not promoted in the plugin.
+
+- **[git-guardrails-claude-code](./git-guardrails-claude-code/SKILL.md)**: Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, etc.) before they execute.
+- **[migrate-to-shoehorn](./migrate-to-shoehorn/SKILL.md)**: Migrate test files from `as` type assertions to @total-typescript/shoehorn.
+- **[scaffold-exercises](./scaffold-exercises/SKILL.md)**: Create exercise directory structures with sections, problems, solutions, and explainers.
+- **[setup-pre-commit](./setup-pre-commit/SKILL.md)**: Set up Husky pre-commit hooks with lint-staged, Prettier, type checking, and tests.

package/skills/mattpocock/skills/misc/git-guardrails-claude-code/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: git-guardrails-claude-code
+description: Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
+---
+
+# Setup Git Guardrails
+
+Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them.
+
+## What Gets Blocked
+
+- `git push` (all variants including `--force`)
+- `git reset --hard`
+- `git clean -f` / `git clean -fd`
+- `git branch -D`
+- `git checkout .` / `git restore .`
+
+When blocked, Claude sees a message telling it that it does not have authority to access these commands.
+
+## Steps
+
+### 1. Ask scope
+
+Ask the user: install for **this project only** (`.claude/settings.json`) or **all projects** (`~/.claude/settings.json`)?
+
+### 2. Copy the hook script
+
+The bundled script is at: [scripts/block-dangerous-git.sh](scripts/block-dangerous-git.sh)
+
+Copy it to the target location based on scope:
+
+- **Project**: `.claude/hooks/block-dangerous-git.sh`
+- **Global**: `~/.claude/hooks/block-dangerous-git.sh`
+
+Make it executable with `chmod +x`.
+
+### 3. Add hook to settings
+
+Add to the appropriate settings file:
+
+**Project** (`.claude/settings.json`):
+
+```json
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+**Global** (`~/.claude/settings.json`):
+
+```json
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "~/.claude/hooks/block-dangerous-git.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+If the settings file already exists, merge the hook into the existing `hooks.PreToolUse` array. Don't overwrite other settings.
+
+### 4. Ask about customization
+
+Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.
+
+### 5. Verify
+
+Run a quick test:
+
+```bash
+echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>
+```
+
+Should exit with code 2 and print a BLOCKED message to stderr.

package/skills/mattpocock/skills/misc/git-guardrails-claude-code/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Git Guardrails for Claude Code"
+  short_description: "Block dangerous git commands"