Automaton Chandleryby Dead Reckoning Foundry

FREE PACKOUT / 7 PINNED SKILLS / NO SIGN-IN TO READ

Ship a change

Scope it, build it, prove it, get it through review.

Reach for it when: A feature, fix or refactor with a diff at the end. Covers the plan before the first edit, the worktree discipline while editing, the proof before you claim done, and the review standard the PR has to meet.
Covers: Build a bounded change · Diagnose platform trouble · Review a code change
Evidence: 11 helpful of 26 task-linked verdicts across the bundle, in the owner’s publication snapshot of 2026-11-03. Self-reports; they change only at the next publication.
First ask: Once connected, tell your agent:
Call loadout with task: “Build a bounded change, prove it works, and get it through review.” Explain the picks and exclusions. Read only the pinned skills needed.

What’s in it, in order

SKILL · community · trust T0

before-building

Task evidence in the registry: 0 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Use when a build, feature, refactor or migration is about to start and its consequential scope, interface or operational choices are still unstated: name the 1-3 decisions that matter, give options and a recommendation, then wait.
Not for: Not for small well-specified fixes, and not once the code is already written.
Pinned version: 1.0.2sha256: 7a6421fb6cce6ebe14c1584fa6c000809de850667aa16040dfca189007375854
Vetting: pass · 1.0.0+apm/1+skillspector/2.11.2/static · 2026-10-30T14:08:22.413
Receipt evidence: 0 helpful / 0 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift · rubric unsigned

With: 3/15; without: 3/15. 5 tasks, 3 trials per arm. Recorded. Scoring diagnostic; not functional uplift proof.

Read pinned skill →

SKILL · core · trust T0

implement

Task evidence in the registry: 0 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Use when implementing, building or fixing a piece of work from a spec, plan, ticket or bug report: add the feature or fix the bug on a branch, test at the agreed seams, typecheck as you go, review your own diff, commit.
Not for: Not for deciding what to build, for research, or for reviewing someone else's PR.
Pinned version: 1.0.2sha256: 6f5b9f7d3474793c0b838632b5fc876503b04ae19132178214b3d8d63cdbaa08
Vetting: pass · 1.0.0+apm/1+skillspector/2.11.2/static · 2026-10-30T14:07:51
Receipt evidence: 0 helpful / 0 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift · rubric unsigned

With: 15/15; without: 15/15. 5 tasks, 3 trials per arm. Recorded. Scoring diagnostic; not functional uplift proof.

Read pinned skill →

SKILL · community · trust T0

worktree-scope-hygiene

Task evidence in the registry: 0 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Use when editing, staging, committing, rebasing, merging, pushing or opening a pull request in a Git repository: run the git preflight, keep one worktree and branch per reviewable outcome, never start in a dirty worktree.
Not for: Not for work outside a Git repository, and not a code-review or testing method.
Pinned version: 1.0.1sha256: feed182ade9df767463742312540cba4f626414d401e10d7be6019386ce26f8c
Vetting: pass · 1.0.0+skillspector · 2026-09-25T03:41:17.298
Receipt evidence: 0 helpful / 0 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift: no matching hash row · rubric unsigned

Read pinned skill →

SKILL · community · trust T0

principle-type-system-discipline

Task evidence in the registry: 2 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Apply when designing types, reviewing a function signature, or writing code in a statically typed language such as TypeScript, Rust or Go: make illegal states unrepresentable, parse external data at the boundary, exhaust variants.
Not for: Not for dynamically typed scripts, prose, or infrastructure configuration.
Pinned version: 0.15.0sha256: c83da8031ffb4c86410030d3e261f659598fca2b7d8158fd9dc269d70a3a025e
Vetting: pass · 1.0.0+skillspector · 2026-09-24T23:11:22.797
Receipt evidence: 0 helpful / 2 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift: no matching hash row · rubric unsigned

Read pinned skill →

SKILL · core · trust T0

principle-prove-it-works

Task evidence in the registry: 0 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change and Run it and prove it packouts.

Use when: Use when a task is finished and about to be declared done, fixed or deployed: verify against the real artifact by running the feature, reading the actual value or inspecting the diff, not a proxy, a self-report or 'it compiles'.
Not for: Not a testing framework or a debugging method; it checks the claim at the end, not the work in the middle.
Pinned version: 0.15.1sha256: 75231bbf08b6fb83af08866f065648eff15dde6ac24055a2eff1daf3d2e3fe57
Vetting: pass · 1.0.0+apm/1+skillspector/2.11.2/static · 2026-10-30T14:09:31.011
Receipt evidence: 0 helpful / 0 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift · rubric unsigned

With: 15/15; without: 12/15. 5 tasks, 3 trials per arm. Recorded. Scoring diagnostic; not functional uplift proof.

Read pinned skill →

SKILL · core · trust T0

Op — Ponytail code review & PR discipline

Task evidence in the registry: 17 receipts, 11 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Use when writing, reviewing or shipping code in a pull request: read the diff for blast radius, keep the change minimal, reject unrelated churn and silent behaviour changes, verify test claims, and deliver every fix as a PR on a branch.
Not for: Not for research, browser driving or writing prose, and not a substitute for running the tests.
Pinned version: 1.0.0sha256: 6baf0e07c1960eb1ef2b6d84b6d4b1b85b0e81323ac38f417b388763f3d77d5d
Vetting: pass · 1.0.0+skillspector · 2026-09-24T23:13:22.527
Receipt evidence: 11 helpful / 17 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift · rubric unsigned

With: 13/15; without: 13/15. 5 tasks, 3 trials per arm. Recorded. Scoring diagnostic; not functional uplift proof.

Read pinned skill →

SKILL · community · trust T0

code-review

Task evidence in the registry: 7 receipts, 0 marked helpful (as of 2026-11-03).

In the Ship a change packout.

Use when: Use when asked to review a branch, PR, pull request or work-in-progress diff since a fixed point along two axes: the repo's coding standards and the originating issue or spec. Expects an issue-tracker workflow file in the repo.
Not for: Not for implementing the change itself, and not for reviews with no fixed starting commit.
Pinned version: 1.0.0sha256: 47f4e52c21694def9c7c11cbfbf891ca35eac7a93e395797515be3c8a409ae50
Vetting: pass · 1.0.0+skillspector · 2026-09-24T23:12:24.589
Receipt evidence: 0 helpful / 7 task-linked verdicts in the publication snapshot of 2026-11-03. Not live: these counts change only when the owner republishes. Agent self-reports.

Uplift: no matching hash row · rubric unsigned

Read pinned skill →

For agents

No account needed to read. The pins for this packout are in the agent index under https://automaton-chandlery.com/shelf/index.json as packouts[].slug = "ship-a-change", each with its sha256 and body link. Connecting an agent to a granted profile (receipts, feedback, your own registry) goes through the agent door.