Promote Develop to Main

.agents/skills/README.md

@@ -2,6 +2,6 @@
 
 Canonical source for the fleet's Claude Code / opencode / Codex Skills, one directory per skill: `<name>/SKILL.md` plus optional `scripts/` and `references/`. This is the only place a skill's content is hand-authored. Everything else derived from it is generated, never hand-edited.
 
-Codex and opencode read this directory directly (`.agents/skills/<name>/SKILL.md`), no install step required, walking from a downstream repo's working directory up to its own repository root. Claude Code does not scan this path. `scripts/build_dist.py` generates a Claude-plugin-compatible copy at `.claude-plugin/fleet-skills/`, published through `.claude-plugin/marketplace.json`.
+Codex and opencode read this directory directly (`.agents/skills/<name>/SKILL.md`), no install step required, walking from a downstream repo's working directory up to its own repository root. Claude Code does not scan this path. GitHub Copilot discovers repository skills under `.github/skills/`. `scripts/build_dist.py` generates both the GitHub tree and a Claude-plugin-compatible copy at `.claude-plugin/fleet-skills/`, published through `.claude-plugin/marketplace.json`.
 
 See `AGENTS.md` for how a repo depends on these skills and `scripts/README.md` for `build_dist.py` and the installer. The procedure for creating, changing, or retiring a skill is the `skill-lifecycle` skill (`skill-lifecycle/SKILL.md` here), which this README defers to.

.agents/skills/add-host-tool/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: add-host-tool
+description: >-
+  Adds or changes a managed host tool across the ptr727/ProjectTemplate fleet contract, Linux and
+  Windows installers, platform documentation, and tests. Use this whenever adding, removing,
+  renaming, or changing the source, probe, version floor, install, report, upgrade, or dry-run
+  behavior of a tool in host-setup or spec/host-tools.json. Triggers even when the request names
+  only one platform, because a required fleet tool needs an executable remedy everywhere it
+  applies and native verification must stay on the platform being tested.
+---
+
+# Add Host Tool
+
+## Establish the Contract
+
+1. Read the issue and all follow-up comments before choosing a source or package identifier.
+2. Add the tool to `spec/host-tools.json` in name order.
+3. Use the executable's real version banner for the probe and pattern.
+4. Set a floor only when it is measured or anchored to every supported distribution.
+5. Provide `source` and executable `remedy` entries for every applicable platform.
+
+## Implement Each Platform
+
+- Keep the existing named-tool interface and default selection behavior.
+- Prefer the distribution package when it meets the floor.
+- Use the platform's established package manager and official package identifier.
+- Keep install and upgrade idempotent.
+- Before an apt-managed install, detect and remove an unowned downloaded copy that shadows it.
+- Before a downloaded install, detect and remove a conflicting package-managed copy.
+- Preserve report, list, explicit selection, install, upgrade, reinstall, and dry-run behavior.
+- Do not test a Windows mutation on Linux or a Linux mutation on Windows.
+
+When a platform is unavailable, verify its registry and tests without claiming a native install. Hand off the exact native commands and expected observations to the operator.
+
+## Update the Complete Surface
+
+Update the platform installers, `spec/host-tools.json`, `docs/host-setup.md`, and the applicable platform READMEs. Update installer and host-gate tests for selection, reporting, installation, upgrade, and dry-run behavior. Sweep prose that describes tool sources or the managed set.
+
+## Verify
+
+1. Run the spec validator and the focused installer and host-gate tests.
+2. Run the repository's formatting, lint, type, and test gates required by the changed files.
+3. On the current native platform, exercise list and report first.
+4. Exercise install and upgrade dry runs.
+5. Apply the install, repeat it to prove idempotence, and run the host gate.
+6. Record untested platforms explicitly and leave cross-platform verification open.

.agents/skills/code-review/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: code-review
+description: >-
+  Reviews a pull request or change set against the repository's contracts, with explicit diff
+  coverage and no suppressed findings. Use this whenever asked to review code, a pull request,
+  a patch, or a proposed change, and whenever GitHub Copilot performs code review. Triggers even
+  when the diff is documentation-only or workflow-only, because the review must load the
+  applicable general, language, documentation, and workflow skills before judging the change.
+---
+
+# Code Review
+
+## Establish the Contract
+
+1. Read the root `AGENTS.md` and the sections it routes to for the changed paths.
+2. Read the complete diff and enumerate every changed file before forming findings.
+3. Load every applicable sibling skill from the current skill distribution:
+   - `comment-and-doc-style` for Markdown, prose, comments, commit messages, and PR titles.
+   - `dotnet-codestyle` for C# and .NET changes.
+   - `python-codestyle` for Python changes.
+   - `shell-codestyle` for shell changes.
+   - `workflow-ci-contract` for GitHub Actions and CI/CD changes.
+4. Treat a missing executable on `PATH` as no evidence that its check is unavailable. Read the
+   repository's documented local invocation before reporting a check as skipped.
+
+Do not substitute a familiar convention for the repository's written contract. Report a
+conflict between instructions instead of silently choosing one.
+
+## Review the Change
+
+Review for correctness, regressions, security, compatibility, error handling, concurrency,
+resource lifetime, tests, and contract drift. Follow data and control flow beyond the edited
+lines when the behavior depends on unchanged callers or consumers.
+
+For each candidate finding:
+
+1. Verify it against the current head tree, not an unfetched checkout or the base branch.
+2. Identify the concrete failing behavior and the conditions that reach it.
+3. Confirm that the repository does not already prevent it elsewhere.
+4. Prefer one root-cause finding over several symptoms of the same defect.
+5. Omit pure preferences that no repository rule or user-visible risk supports.
+
+Review carried fleet content by intent and fidelity. A byte-locked reference to a path that one
+downstream repository does not carry is not a broken link. A substantive defect in canonical
+content remains a finding, with the fix located at its canonical source.
+
+## Publish Every Finding
+
+Never suppress or hide a finding because confidence is low. Investigate until it is supported
+or discard it. Publish every supported finding as an inline review comment when a changed line
+can anchor it. Use the review body only when no valid inline anchor exists.
+
+Each finding states:
+
+- A concise imperative title with a severity.
+- The file and smallest useful line range.
+- The behavior that fails and the input or state that triggers it.
+- Why the change causes the failure.
+- A bounded direction for the fix when one is known.
+
+Do not report a clean review until every changed file has been read. End the review body with
+exactly one ASCII marker, replacing the numbers with measured counts:
+
+```text
+<!-- fleet-review: reviewed=N changed=N findings=N -->
+```
+
+`reviewed` is the number of changed files actually reviewed. `changed` is the total number of
+changed files. `findings` is the number of published findings, including body-only findings.
+Never emit `reviewed=changed` as a placeholder. If full coverage is impossible, emit the actual
+counts and explain the limitation in the review body.

.agents/skills/copilot-instructions-keeper/SKILL.md

@@ -18,10 +18,10 @@ description: >-
 
 ## Why this exists
 
-`.github/copilot-instructions.md` is read directly by the GitHub Copilot review bot, which
-cannot read a `SKILL.md`. Unlike other carried governance content, its rule text is never
-pointer-ized into a skill, this file always stays fully intact in every repo that carries it.
-This skill is about maintaining that file's carried copy, not a substitute for it.
+`.github/copilot-instructions.md` is read directly by GitHub Copilot and bootstraps the shared
+`AGENTS.md` instruction set and review-focused skills. Its Copilot-specific rules stay fully
+intact in every repo that carries it. This skill maintains that carried copy, it does not replace
+the bootstrap.
 
 `spec/files.json` declares it `intent` fidelity, `whole: true`, covering three named sections
 (`Commit Messages and Pull Request Titles`, `Reviewing Carried Fleet Content`, `GitHub Copilot

.agents/skills/pr-review-conduct/SKILL.md

@@ -13,9 +13,9 @@ description: >-
   full diff, or left a suppressed low-confidence finding, which opens no thread at all,
   unanswered. Also triggers when a review loop looks stuck
   (no review landing, findings that keep reappearing) or when deciding a finding is real, false,
-  deferred, or a deliberate decline. Provider-specific mechanics (GitHub Copilot's request/poll/
-  reply API calls) live in .github/copilot-instructions.md's "GitHub Copilot Review Runbook,"
-  this skill is the contract that runbook implements, not a replacement for it.
+  deferred, or a deliberate decline. Provider-specific mechanics are implemented by
+  scripts/pr_review.py and bootstrapped by .github/copilot-instructions.md. This skill is the
+  contract those surfaces implement, not a replacement for them.
 ---
 
 # PR Review Conduct
@@ -124,7 +124,8 @@ reviewer's own words to identify it), give one bold verdict per finding (`Fixed
 `Disproven`, or `No change needed`), state the `(N)` count the block gave so answers can be
 checked against findings, and link the review round. **Read every round, not only the head.** A
 suppressed finding does not retire when a later push supersedes it, it just stops showing up in a
-head-scoped query while still unanswered.
+head-scoped query while still unanswered. Post the answer with `scripts/pr_review.py comment`
+from a hub checkout. Do not use a provider connector or reconstruct the GitHub mutation.
 
 ## Escalate to the maintainer when
 
@@ -134,13 +135,12 @@ head-scoped query while still unanswered.
 - A finding is judged real but should not be fixed. That decision is never the agent's alone.
 - An architectural redesign is proposed rather than a bug fix.
 
-## Mechanics live elsewhere
+## Mechanics Live Elsewhere
 
-This skill is the provider-agnostic contract. For the actual GitHub API calls, requesting a
-Copilot review, polling for it, matching the suppressed-findings heading (its wording has moved
-more than once), verifying head-SHA and diff coverage, replying and resolving threads without a
-hand-typed id, see `.github/copilot-instructions.md` "GitHub Copilot Review Runbook" in the repo
-being worked in, and reach for `scripts/pr_review.py` (hub-hosted, invoked from a hub checkout)
-before hand-rolling any of it. `status` reports coverage, threads, suppressed findings, and shapes
-in one call, `wait` backs off in-process, and `reply` resolves a thread by matching the finding's
-own words rather than a line number a fix push can move.
+This skill is the provider-agnostic contract. Use `scripts/pr_review.py` from a hub checkout for
+the GitHub-specific API operations. `status` reports coverage, threads, body-only findings, and
+shapes in one call. `wait` requests and polls in-process. `comment` posts a PR-conversation
+answer after it reads the PR node ID. `reply` resolves a thread by matching the finding's own
+words instead of a line number a fix push can move. The repository's
+`.github/copilot-instructions.md` bootstraps Copilot into the `code-review` skill and its stable
+coverage marker. Do not reconstruct the API operations by hand.

.agents/skills/python-codestyle/SKILL.md

@@ -89,6 +89,13 @@ chaining, so it runs the same on any task shell) is in the hub `vscode-tasks-pyt
 CI runs the same clean-compile commands as the authoritative backstop. Git hooks are opt-in, so
 wire `pre-commit` for `ruff` and the type checker yourself if you want local enforcement.
 
+A restricted executor gives each task a cache directory under a writable temporary root. Point
+`UV_CACHE_DIR`, `RUFF_CACHE_DIR`, `MYPY_CACHE_DIR`, and `COVERAGE_FILE` into that directory before
+running the applicable tools. This keeps their generated state outside both the home directory
+and the checkout. Do not change `HOME` or an agent configuration directory. A denied network
+request means the tool did not run, so preserve the denial and rerun through the executor's scoped
+approval mechanism.
+
 ## Layout
 
 `src` layout, which keeps the package out of the repo root and prevents accidental imports of

.agents/skills/repo-worktree/SKILL.md

@@ -5,7 +5,8 @@ description: >-
   including a continuation of a prior session's task, creates its own git worktree on its own
   feature branch before its first file edit, based on the branch work starts on (develop on both
   fleet workflow models unless the task is explicitly about main-only content, never whichever
-  branch a tool defaulted to). Also wraps the mechanics:
+  branch a tool defaulted to), with a standalone-clone fallback when an executor cannot write
+  both the standard worktree and its Git metadata. Also wraps the mechanics:
   creating a worktree with git worktree add, the fleet layout convention, listing what is in
   flight, and removing a worktree and its branch after merge. Use this whenever about to create
   or edit files in a fleet repo, whenever starting or resuming a task, whenever the task's
@@ -97,6 +98,33 @@ git -C ~/repos/<Repo> fetch origin develop
 git -C ~/repos/<Repo> worktree add ~/repos/worktrees/<Repo>-<task-slug> -b <task-branch> origin/develop
 ```
 
+Before choosing that path, inspect the executor's active write boundaries. A linked worktree
+requires write access to both of these locations:
+
+- the intended `~/repos/worktrees/<Repo>-<task-slug>` worktree directory
+- the base clone's `.git/worktrees/` administrative directory, which holds the index and locks
+
+A writable worktree directory does not make the administrative directory writable.
+
+Use the standard layout when both locations are writable. When either location is outside the
+write boundary, create a standalone clone under a writable temporary root. Name it
+`<temporary-root>/<Repo>-<task-slug>`, fetch immediately, and create the task branch from
+`origin/develop`. A standalone clone keeps its worktree and Git administrative directory under
+the same writable root. It therefore supports edits, explicit-path staging, commits, and branch
+updates without sharing the base clone's index.
+
+```sh
+TASK_ORIGIN="$(git -C <base-clone> remote get-url origin)"
+git clone --no-checkout "$TASK_ORIGIN" <temporary-root>/<Repo>-<task-slug>
+git -C <temporary-root>/<Repo>-<task-slug> fetch origin develop
+git -C <temporary-root>/<Repo>-<task-slug> switch -c <task-branch> origin/develop
+```
+
+Do not use a linked worktree under the temporary root when the base clone's Git metadata is
+read-only. If an existing linked worktree must be kept, index operations require the executor's
+scoped approval for that administrative path. Prefer the standalone clone so ordinary Git work
+does not require repeated approval.
+
 A continuation attaches the task's existing branch rather than forking a fresh one:
 
 ```sh
@@ -129,6 +157,9 @@ GitHub default branch, which is the wrong path and the wrong base here. Create t
   in flight across the whole fleet.
 - After the task's pull request merges, remove the worktree and its branch from the base clone:
   `git worktree remove ~/repos/worktrees/<Repo>-<task-slug>`, then `git branch -d <task-branch>`.
+- After the task's pull request merges, remove a temporary standalone clone at its exact
+  `<temporary-root>/<Repo>-<task-slug>` path. The remote branch follows the repository's normal
+  pull request cleanup policy.
 - A worktree that refuses removal is dirty, and force is not the fix: look at what is
   uncommitted in it first, since discarding uncommitted work runs only on explicit instruction,
   per the `git-commit-conventions` skill.