one-code-extension 0.4.0 → 0.5.0

package/skills/code-review/cells/max-5x5-verify-sweep.md

@@ -0,0 +1,162 @@
+`max effort → 5+5 angles × 8 candidates → 1-vote verify → sweep → ≤15 findings`
+
+You are reviewing for **recall** at maximum effort: catch every real bug. At
+this level, catching real bugs matters more than avoiding false positives — a
+missed bug ships. Err on the side of surfacing.
+
+## Phase 0 — Gather the diff
+
+Run `git diff @{upstream}...HEAD` (or `git diff main...HEAD` / `git diff HEAD~1`
+if there's no upstream) to get the unified diff under review. If there are
+uncommitted changes, or the range diff is empty, also run `git diff HEAD` and
+include the working-tree changes in scope — the review often runs before the
+commit. If a PR number, branch name, or file path was passed as an argument,
+review that target instead. Treat this diff as the review scope.
+
+## Phase 1 — Find candidates (5 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 8 each)
+
+Run **10 independent finder angles** via the Agent tool. Each
+surfaces **up to 8 candidate findings**. Do NOT let one angle's conclusions
+suppress another's — if two angles flag the same line for different reasons,
+record both. If the Agent tool is not available in your current tool set, do not error — perform each angle (and each verification) yourself, sequentially, in this context.
+
+### Angle A — line-by-line diff scan
+
+Read every hunk in the diff, line by line. Then Read the enclosing function for
+each hunk — bugs in unchanged lines of a touched function are in scope (the PR
+re-exposes or fails to fix them). For every line ask: what input, state, timing,
+or platform makes this line wrong? Look for inverted/wrong conditions,
+off-by-one, null/undefined deref, missing `await`, falsy-zero checks,
+wrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.
+
+### Angle B — removed-behavior auditor
+
+For every line the diff DELETES or replaces, name the invariant or behavior it
+enforced, then search the new code for where that invariant is re-established.
+If you can't find it, that's a candidate: a removed guard, a dropped error
+path, a narrowed validation, a deleted test that was covering a real case.
+
+### Angle C — cross-file tracer
+
+For each function the diff changes, find its callers (Grep for the symbol) and
+check whether the change breaks any call site: a new precondition, a changed
+return shape, a new exception, a timing/ordering dependency. Also check callees:
+does a parallel change in the same PR make a call unsafe?
+
+### Angle D — language-pitfall specialist
+
+Scan for the classic pitfalls of the diff's language/framework — for example:
+JS falsy-zero, `==` coercion, closure-captured loop var; Python mutable default
+args, late-binding closures; Go nil-map write, range-var capture; SQL injection;
+timezone/DST drift; float equality. Flag any instance the diff introduces.
+
+### Angle E — wrapper/proxy correctness
+
+When the PR adds or modifies a type that wraps another (cache, proxy, decorator,
+adapter): check that every method routes to the wrapped instance and not back
+through a registry/session/global — e.g. a caching provider holding a
+`delegate` field that resolves IDs via `session.get(...)` instead of
+`delegate.get(...)` will re-enter the cache or recurse. Also check that the
+wrapper forwards all the methods the callers actually use.
+
+### Reuse
+
+The angles above hunt for bugs; this one and the next two hunt for cleanup in
+the changed code. Flag new code that re-implements something the codebase
+already has — Grep shared/utility modules and files adjacent to the change,
+and name the existing helper to call instead.
+
+### Simplification
+
+Flag unnecessary complexity the diff adds: redundant or derivable state,
+copy-paste with slight variation, deep nesting, dead code left behind. Name
+the simpler form that does the same job.
+
+### Efficiency
+
+Flag wasted work the diff introduces: redundant computation or repeated I/O,
+independent operations run sequentially, blocking work added to startup or
+hot paths. Also flag long-lived objects built from closures or captured
+environments — they keep the entire enclosing scope alive for the object's
+lifetime (a memory leak when that scope holds large values); prefer a
+class/struct that copies only the fields it needs. Name the cheaper
+alternative.
+
+### Altitude
+
+Check that each change fixes the root cause at the right depth rather than
+patching a symptom with a fragile bandaid. Special cases layered on shared
+infrastructure are a sign the fix isn't deep enough — prefer the simpler, more
+general change to the underlying mechanism over adding special cases, and name
+that change.
+
+### Conventions (CLAUDE.md)
+
+Find the CLAUDE.md files that govern the changed code: the user-level
+~/.claude/CLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or
+CLAUDE.local.md in a directory that is an ancestor of a changed file (a
+directory's CLAUDE.md only applies to files at or below it). Read each one
+that exists, then check the diff for clear violations of the rules they state.
+
+Only flag a violation when you can quote the exact rule and the exact line
+that breaks it — no style preferences, no vague "spirit of the doc"
+inferences. In the finding, name the CLAUDE.md path and quote the rule so the
+report can cite it. If no CLAUDE.md applies, return nothing for this angle.
+
+Cleanup, altitude, and conventions candidates use the same
+`file`/`line`/`summary` shape; in `failure_scenario`, state the concrete
+cost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule
+is broken) instead of a crash. Correctness bugs always outrank cleanup,
+altitude, and conventions findings when the output cap forces a cut.
+
+## Phase 2 — Verify (1-vote, 3-state)
+
+Dedup candidates that point at the same line/mechanism, keeping the one with
+the most concrete failure scenario. For each remaining candidate, run **one
+verifier** via the Agent tool: give it the diff, the relevant
+file(s), and the candidate, and have it return exactly one of:
+
+- **CONFIRMED** — can name the inputs/state that trigger it and the wrong
+  output or crash. Quote the line.
+- **PLAUSIBLE** — mechanism is real, trigger is uncertain (timing, env,
+  config). State what would confirm it.
+- **REFUTED** — factually wrong (code doesn't say that) or guarded elsewhere.
+  Quote the line that proves it.
+
+Keep candidates where the vote is CONFIRMED or PLAUSIBLE.
+
+This is recall mode — a single non-REFUTED vote carries the finding. Do NOT
+drop on uncertainty.
+
+## Phase 3 — Sweep for gaps
+
+Run **one more finder** as a fresh reviewer who has the verified list. Re-read
+the diff and enclosing functions looking ONLY for defects not already listed.
+Do not re-derive or re-confirm anything already there — the job is gaps. Focus
+on what the first pass tends to miss: moved/extracted code that dropped a guard
+or anchor; second-tier footguns (dataclass default evaluated once, `hash()`
+non-determinism, lock-scope shrink, predicate methods with side effects);
+setup/teardown asymmetry in tests; config defaults flipped.
+
+Surface **up to 8 additional candidates**, each naming a defect not already on
+the list. If nothing new, return an empty sweep — do not pad.
+
+## Output
+
+Return findings as a JSON array of at most 15 objects:
+
+```json
+[
+  {
+    "file": "path/to/file.ext",
+    "line": 123,
+    "summary": "one-sentence statement of the bug",
+    "failure_scenario": "concrete inputs/state → wrong output/crash"
+  }
+]
+```
+
+Ranked most-severe first. If more than 15 survive, keep the 15 most
+severe. If nothing survives verification, return `[]`. Do not call the
+ReportFindings tool even if it is available - this review's
+output contract is the JSON block above.

package/skills/code-review/cells/medium-3x5-verify.md

@@ -0,0 +1,132 @@
+`medium effort → 3+5 angles × 6 candidates → 1-vote verify → ≤8 findings`
+
+You are reviewing for **precision** at medium effort: every finding you surface
+should be one a maintainer would act on.
+
+## Phase 0 — Gather the diff
+
+Run `git diff @{upstream}...HEAD` (or `git diff main...HEAD` / `git diff HEAD~1`
+if there's no upstream) to get the unified diff under review. If there are
+uncommitted changes, or the range diff is empty, also run `git diff HEAD` and
+include the working-tree changes in scope — the review often runs before the
+commit. If a PR number, branch name, or file path was passed as an argument,
+review that target instead. Treat this diff as the review scope.
+
+## Phase 1 — Find candidates (3 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 6 each)
+
+Run **8 independent finder angles** via the Agent tool. Each
+surfaces **up to 6 candidate findings** with `file`, `line`, a one-line
+`summary`, and a concrete `failure_scenario`. If the Agent tool is not available in your current tool set, do not error — perform each angle (and each verification) yourself, sequentially, in this context.
+
+### Angle A — line-by-line diff scan
+
+Read every hunk in the diff, line by line. Then Read the enclosing function for
+each hunk — bugs in unchanged lines of a touched function are in scope (the PR
+re-exposes or fails to fix them). For every line ask: what input, state, timing,
+or platform makes this line wrong? Look for inverted/wrong conditions,
+off-by-one, null/undefined deref, missing `await`, falsy-zero checks,
+wrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.
+
+### Angle B — removed-behavior auditor
+
+For every line the diff DELETES or replaces, name the invariant or behavior it
+enforced, then search the new code for where that invariant is re-established.
+If you can't find it, that's a candidate: a removed guard, a dropped error
+path, a narrowed validation, a deleted test that was covering a real case.
+
+### Angle C — cross-file tracer
+
+For each function the diff changes, find its callers (Grep for the symbol) and
+check whether the change breaks any call site: a new precondition, a changed
+return shape, a new exception, a timing/ordering dependency. Also check callees:
+does a parallel change in the same PR make a call unsafe?
+
+### Reuse
+
+The angles above hunt for bugs; this one and the next two hunt for cleanup in
+the changed code. Flag new code that re-implements something the codebase
+already has — Grep shared/utility modules and files adjacent to the change,
+and name the existing helper to call instead.
+
+### Simplification
+
+Flag unnecessary complexity the diff adds: redundant or derivable state,
+copy-paste with slight variation, deep nesting, dead code left behind. Name
+the simpler form that does the same job.
+
+### Efficiency
+
+Flag wasted work the diff introduces: redundant computation or repeated I/O,
+independent operations run sequentially, blocking work added to startup or
+hot paths. Also flag long-lived objects built from closures or captured
+environments — they keep the entire enclosing scope alive for the object's
+lifetime (a memory leak when that scope holds large values); prefer a
+class/struct that copies only the fields it needs. Name the cheaper
+alternative.
+
+### Altitude
+
+Check that each change fixes the root cause at the right depth rather than
+patching a symptom with a fragile bandaid. Special cases layered on shared
+infrastructure are a sign the fix isn't deep enough — prefer the simpler, more
+general change to the underlying mechanism over adding special cases, and name
+that change.
+
+### Conventions (CLAUDE.md)
+
+Find the CLAUDE.md files that govern the changed code: the user-level
+~/.claude/CLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or
+CLAUDE.local.md in a directory that is an ancestor of a changed file (a
+directory's CLAUDE.md only applies to files at or below it). Read each one
+that exists, then check the diff for clear violations of the rules they state.
+
+Only flag a violation when you can quote the exact rule and the exact line
+that breaks it — no style preferences, no vague "spirit of the doc"
+inferences. In the finding, name the CLAUDE.md path and quote the rule so the
+report can cite it. If no CLAUDE.md applies, return nothing for this angle.
+
+Cleanup, altitude, and conventions candidates use the same
+`file`/`line`/`summary` shape; in `failure_scenario`, state the concrete
+cost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule
+is broken) instead of a crash. Correctness bugs always outrank cleanup,
+altitude, and conventions findings when the output cap forces a cut.
+
+Pass every candidate with a nameable failure scenario through — finders that
+silently drop half-believed candidates bypass the verify step and are the
+dominant cause of misses.
+
+## Phase 2 — Verify (1-vote, 3-state)
+
+Dedup candidates that point at the same line/mechanism, keeping the one with
+the most concrete failure scenario. For each remaining candidate, run **one
+verifier** via the Agent tool: give it the diff, the relevant
+file(s), and the candidate, and have it return exactly one of:
+
+- **CONFIRMED** — can name the inputs/state that trigger it and the wrong
+  output or crash. Quote the line.
+- **PLAUSIBLE** — mechanism is real, trigger is uncertain (timing, env,
+  config). State what would confirm it.
+- **REFUTED** — factually wrong (code doesn't say that) or guarded elsewhere.
+  Quote the line that proves it.
+
+Keep candidates where the vote is CONFIRMED or PLAUSIBLE.
+
+## Output
+
+Return findings as a JSON array of at most 8 objects:
+
+```json
+[
+  {
+    "file": "path/to/file.ext",
+    "line": 123,
+    "summary": "one-sentence statement of the bug",
+    "failure_scenario": "concrete inputs/state → wrong output/crash"
+  }
+]
+```
+
+Ranked most-severe first. If more than 8 survive, keep the 8 most
+severe. If nothing survives verification, return `[]`. Do not call the
+ReportFindings tool even if it is available - this review's
+output contract is the JSON block above.

package/skills/code-review/cells/minimal-prompt.md

@@ -0,0 +1,32 @@
+`minimal prompt → single careful diff pass → ≤15 findings`
+
+You are reviewing a pull request for real bugs. Run `git diff @{upstream}...HEAD` (or `git diff main...HEAD` / `git diff HEAD~1`
+if there's no upstream) to get the unified diff under review. If there are
+uncommitted changes, or the range diff is empty, also run `git diff HEAD` and
+include the working-tree changes in scope — the review often runs before the
+commit. If a PR number, branch name, or file path was passed as an argument,
+review that target instead. Treat this diff as the review scope.
+
+Review the diff as a careful senior engineer would: read every hunk, open the surrounding files for context as needed (Read, Grep, git log/blame/show), and hunt for correctness issues — wrong or inverted conditions, off-by-one, null/undefined dereference, missing `await`, dropped error handling, removed guards or validations, broken callers of changed functions, races. Prefer real failure modes over style; every finding needs a concrete scenario in which the code misbehaves.
+
+When you are done, report at most 15 findings in the output format below — for each: the file path and start line, a one-sentence summary, and the concrete scenario in which the code misbehaves. Quality over quantity: include everything you genuinely believe is a real issue, and nothing you don't.
+
+## Output
+
+Return findings as a JSON array of at most 15 objects:
+
+```json
+[
+  {
+    "file": "path/to/file.ext",
+    "line": 123,
+    "summary": "one-sentence statement of the bug",
+    "failure_scenario": "concrete inputs/state → wrong output/crash"
+  }
+]
+```
+
+Ranked most-severe first. If more than 15 survive, keep the 15 most
+severe. If nothing survives verification, return `[]`. Do not call the
+ReportFindings tool even if it is available - this review's
+output contract is the JSON block above.

package/skills/code-review/cells/xhigh-10-inline-sweep.md

@@ -0,0 +1,149 @@
+`xhigh effort → 10 inline angles → dedup (no verify) → sweep → ≤15 findings`
+
+You are reviewing for **recall** at extra-high effort: catch every real bug. At
+this level, catching real bugs matters more than avoiding false positives — a
+missed bug ships. Err on the side of surfacing.
+
+## Phase 0 — Gather the diff
+
+Run `git diff @{upstream}...HEAD` (or `git diff main...HEAD` / `git diff HEAD~1`
+if there's no upstream) to get the unified diff under review. If there are
+uncommitted changes, or the range diff is empty, also run `git diff HEAD` and
+include the working-tree changes in scope — the review often runs before the
+commit. If a PR number, branch name, or file path was passed as an argument,
+review that target instead. Treat this diff as the review scope.
+
+## Phase 1 — Find candidates (5 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 8 each)
+
+Run **10 independent finder angles** in sequence yourself, in THIS context — do NOT spawn subagents for them. Each
+surfaces **up to 8 candidate findings**. Do NOT let one angle's conclusions
+suppress another's — if two angles flag the same line for different reasons,
+record both.
+
+### Angle A — line-by-line diff scan
+
+Read every hunk in the diff, line by line. Then Read the enclosing function for
+each hunk — bugs in unchanged lines of a touched function are in scope (the PR
+re-exposes or fails to fix them). For every line ask: what input, state, timing,
+or platform makes this line wrong? Look for inverted/wrong conditions,
+off-by-one, null/undefined deref, missing `await`, falsy-zero checks,
+wrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.
+
+### Angle B — removed-behavior auditor
+
+For every line the diff DELETES or replaces, name the invariant or behavior it
+enforced, then search the new code for where that invariant is re-established.
+If you can't find it, that's a candidate: a removed guard, a dropped error
+path, a narrowed validation, a deleted test that was covering a real case.
+
+### Angle C — cross-file tracer
+
+For each function the diff changes, find its callers (Grep for the symbol) and
+check whether the change breaks any call site: a new precondition, a changed
+return shape, a new exception, a timing/ordering dependency. Also check callees:
+does a parallel change in the same PR make a call unsafe?
+
+### Angle D — language-pitfall specialist
+
+Scan for the classic pitfalls of the diff's language/framework — for example:
+JS falsy-zero, `==` coercion, closure-captured loop var; Python mutable default
+args, late-binding closures; Go nil-map write, range-var capture; SQL injection;
+timezone/DST drift; float equality. Flag any instance the diff introduces.
+
+### Angle E — wrapper/proxy correctness
+
+When the PR adds or modifies a type that wraps another (cache, proxy, decorator,
+adapter): check that every method routes to the wrapped instance and not back
+through a registry/session/global — e.g. a caching provider holding a
+`delegate` field that resolves IDs via `session.get(...)` instead of
+`delegate.get(...)` will re-enter the cache or recurse. Also check that the
+wrapper forwards all the methods the callers actually use.
+
+### Reuse
+
+The angles above hunt for bugs; this one and the next two hunt for cleanup in
+the changed code. Flag new code that re-implements something the codebase
+already has — Grep shared/utility modules and files adjacent to the change,
+and name the existing helper to call instead.
+
+### Simplification
+
+Flag unnecessary complexity the diff adds: redundant or derivable state,
+copy-paste with slight variation, deep nesting, dead code left behind. Name
+the simpler form that does the same job.
+
+### Efficiency
+
+Flag wasted work the diff introduces: redundant computation or repeated I/O,
+independent operations run sequentially, blocking work added to startup or
+hot paths. Also flag long-lived objects built from closures or captured
+environments — they keep the entire enclosing scope alive for the object's
+lifetime (a memory leak when that scope holds large values); prefer a
+class/struct that copies only the fields it needs. Name the cheaper
+alternative.
+
+### Altitude
+
+Check that each change fixes the root cause at the right depth rather than
+patching a symptom with a fragile bandaid. Special cases layered on shared
+infrastructure are a sign the fix isn't deep enough — prefer the simpler, more
+general change to the underlying mechanism over adding special cases, and name
+that change.
+
+### Conventions (CLAUDE.md)
+
+Find the CLAUDE.md files that govern the changed code: the user-level
+~/.claude/CLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or
+CLAUDE.local.md in a directory that is an ancestor of a changed file (a
+directory's CLAUDE.md only applies to files at or below it). Read each one
+that exists, then check the diff for clear violations of the rules they state.
+
+Only flag a violation when you can quote the exact rule and the exact line
+that breaks it — no style preferences, no vague "spirit of the doc"
+inferences. In the finding, name the CLAUDE.md path and quote the rule so the
+report can cite it. If no CLAUDE.md applies, return nothing for this angle.
+
+Cleanup, altitude, and conventions candidates use the same
+`file`/`line`/`summary` shape; in `failure_scenario`, state the concrete
+cost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule
+is broken) instead of a crash. Correctness bugs always outrank cleanup,
+altitude, and conventions findings when the output cap forces a cut.
+
+## Phase 2 — Dedup only (no verify)
+
+Pool all candidates. Dedup near-duplicates only (same defect, same location, same reason → keep one). Do NOT run verifiers; do NOT re-judge. Sort by severity. Do NOT drop on uncertainty.
+
+## Phase 3 — Sweep for gaps
+
+Take one more pass (same context — no subagent) as a fresh reviewer who has the deduplicated list. Re-read
+the diff and enclosing functions looking ONLY for defects not already listed.
+Do not re-derive or re-confirm anything already there — the job is gaps. Focus
+on what the first pass tends to miss: moved/extracted code that dropped a guard
+or anchor; second-tier footguns (dataclass default evaluated once, `hash()`
+non-determinism, lock-scope shrink, predicate methods with side effects);
+setup/teardown asymmetry in tests; config defaults flipped.
+
+Surface **up to 8 additional candidates**, each naming a defect not already on
+the list. If nothing new, return nothing from this phase — do not pad.
+
+## Output
+
+Target **at least 7 findings**. If fewer genuine findings exist, emit what you have — do not invent to hit the floor.
+
+Return findings as a JSON array of at most 15 objects:
+
+```json
+[
+  {
+    "file": "path/to/file.ext",
+    "line": 123,
+    "summary": "one-sentence statement of the bug",
+    "failure_scenario": "concrete inputs/state → wrong output/crash"
+  }
+]
+```
+
+Ranked most-severe first. If more than 15 survive, keep the 15 most
+severe. If nothing survives, return `[]`. Do not call the
+ReportFindings tool even if it is available - this review's
+output contract is the JSON block above.

package/skills/code-review/cells/xhigh-5x5-verify-sweep.md

@@ -0,0 +1,162 @@
+`xhigh effort → 5+5 angles × 8 candidates → 1-vote verify → sweep → ≤15 findings`
+
+You are reviewing for **recall** at extra-high effort: catch every real bug. At
+this level, catching real bugs matters more than avoiding false positives — a
+missed bug ships. Err on the side of surfacing.
+
+## Phase 0 — Gather the diff
+
+Run `git diff @{upstream}...HEAD` (or `git diff main...HEAD` / `git diff HEAD~1`
+if there's no upstream) to get the unified diff under review. If there are
+uncommitted changes, or the range diff is empty, also run `git diff HEAD` and
+include the working-tree changes in scope — the review often runs before the
+commit. If a PR number, branch name, or file path was passed as an argument,
+review that target instead. Treat this diff as the review scope.
+
+## Phase 1 — Find candidates (5 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 8 each)
+
+Run **10 independent finder angles** via the Agent tool. Each
+surfaces **up to 8 candidate findings**. Do NOT let one angle's conclusions
+suppress another's — if two angles flag the same line for different reasons,
+record both. If the Agent tool is not available in your current tool set, do not error — perform each angle (and each verification) yourself, sequentially, in this context.
+
+### Angle A — line-by-line diff scan
+
+Read every hunk in the diff, line by line. Then Read the enclosing function for
+each hunk — bugs in unchanged lines of a touched function are in scope (the PR
+re-exposes or fails to fix them). For every line ask: what input, state, timing,
+or platform makes this line wrong? Look for inverted/wrong conditions,
+off-by-one, null/undefined deref, missing `await`, falsy-zero checks,
+wrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.
+
+### Angle B — removed-behavior auditor
+
+For every line the diff DELETES or replaces, name the invariant or behavior it
+enforced, then search the new code for where that invariant is re-established.
+If you can't find it, that's a candidate: a removed guard, a dropped error
+path, a narrowed validation, a deleted test that was covering a real case.
+
+### Angle C — cross-file tracer
+
+For each function the diff changes, find its callers (Grep for the symbol) and
+check whether the change breaks any call site: a new precondition, a changed
+return shape, a new exception, a timing/ordering dependency. Also check callees:
+does a parallel change in the same PR make a call unsafe?
+
+### Angle D — language-pitfall specialist
+
+Scan for the classic pitfalls of the diff's language/framework — for example:
+JS falsy-zero, `==` coercion, closure-captured loop var; Python mutable default
+args, late-binding closures; Go nil-map write, range-var capture; SQL injection;
+timezone/DST drift; float equality. Flag any instance the diff introduces.
+
+### Angle E — wrapper/proxy correctness
+
+When the PR adds or modifies a type that wraps another (cache, proxy, decorator,
+adapter): check that every method routes to the wrapped instance and not back
+through a registry/session/global — e.g. a caching provider holding a
+`delegate` field that resolves IDs via `session.get(...)` instead of
+`delegate.get(...)` will re-enter the cache or recurse. Also check that the
+wrapper forwards all the methods the callers actually use.
+
+### Reuse
+
+The angles above hunt for bugs; this one and the next two hunt for cleanup in
+the changed code. Flag new code that re-implements something the codebase
+already has — Grep shared/utility modules and files adjacent to the change,
+and name the existing helper to call instead.
+
+### Simplification
+
+Flag unnecessary complexity the diff adds: redundant or derivable state,
+copy-paste with slight variation, deep nesting, dead code left behind. Name
+the simpler form that does the same job.
+
+### Efficiency
+
+Flag wasted work the diff introduces: redundant computation or repeated I/O,
+independent operations run sequentially, blocking work added to startup or
+hot paths. Also flag long-lived objects built from closures or captured
+environments — they keep the entire enclosing scope alive for the object's
+lifetime (a memory leak when that scope holds large values); prefer a
+class/struct that copies only the fields it needs. Name the cheaper
+alternative.
+
+### Altitude
+
+Check that each change fixes the root cause at the right depth rather than
+patching a symptom with a fragile bandaid. Special cases layered on shared
+infrastructure are a sign the fix isn't deep enough — prefer the simpler, more
+general change to the underlying mechanism over adding special cases, and name
+that change.
+
+### Conventions (CLAUDE.md)
+
+Find the CLAUDE.md files that govern the changed code: the user-level
+~/.claude/CLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or
+CLAUDE.local.md in a directory that is an ancestor of a changed file (a
+directory's CLAUDE.md only applies to files at or below it). Read each one
+that exists, then check the diff for clear violations of the rules they state.
+
+Only flag a violation when you can quote the exact rule and the exact line
+that breaks it — no style preferences, no vague "spirit of the doc"
+inferences. In the finding, name the CLAUDE.md path and quote the rule so the
+report can cite it. If no CLAUDE.md applies, return nothing for this angle.
+
+Cleanup, altitude, and conventions candidates use the same
+`file`/`line`/`summary` shape; in `failure_scenario`, state the concrete
+cost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule
+is broken) instead of a crash. Correctness bugs always outrank cleanup,
+altitude, and conventions findings when the output cap forces a cut.
+
+## Phase 2 — Verify (1-vote, 3-state)
+
+Dedup candidates that point at the same line/mechanism, keeping the one with
+the most concrete failure scenario. For each remaining candidate, run **one
+verifier** via the Agent tool: give it the diff, the relevant
+file(s), and the candidate, and have it return exactly one of:
+
+- **CONFIRMED** — can name the inputs/state that trigger it and the wrong
+  output or crash. Quote the line.
+- **PLAUSIBLE** — mechanism is real, trigger is uncertain (timing, env,
+  config). State what would confirm it.
+- **REFUTED** — factually wrong (code doesn't say that) or guarded elsewhere.
+  Quote the line that proves it.
+
+Keep candidates where the vote is CONFIRMED or PLAUSIBLE.
+
+This is recall mode — a single non-REFUTED vote carries the finding. Do NOT
+drop on uncertainty.
+
+## Phase 3 — Sweep for gaps
+
+Run **one more finder** as a fresh reviewer who has the verified list. Re-read
+the diff and enclosing functions looking ONLY for defects not already listed.
+Do not re-derive or re-confirm anything already there — the job is gaps. Focus
+on what the first pass tends to miss: moved/extracted code that dropped a guard
+or anchor; second-tier footguns (dataclass default evaluated once, `hash()`
+non-determinism, lock-scope shrink, predicate methods with side effects);
+setup/teardown asymmetry in tests; config defaults flipped.
+
+Surface **up to 8 additional candidates**, each naming a defect not already on
+the list. If nothing new, return an empty sweep — do not pad.
+
+## Output
+
+Return findings as a JSON array of at most 15 objects:
+
+```json
+[
+  {
+    "file": "path/to/file.ext",
+    "line": 123,
+    "summary": "one-sentence statement of the bug",
+    "failure_scenario": "concrete inputs/state → wrong output/crash"
+  }
+]
+```
+
+Ranked most-severe first. If more than 15 survive, keep the 15 most
+severe. If nothing survives verification, return `[]`. Do not call the
+ReportFindings tool even if it is available - this review's
+output contract is the JSON block above.

package/skills/fewer-permission-prompts/SKILL.md

@@ -16,7 +16,7 @@ Then, add these to One Code's per-repo settings at `~/.onecode/projects/<slug>/s
 
 ## Steps
 
-1. **Locate transcripts.** One Code / pi session transcripts live under the agent state dir at `~/.onecode/agent/sessions/<sanitized-cwd>/*.jsonl` (the base honours `PI_CODING_AGENT_DIR`, which the bundled app sets to `~/.onecode/agent`; a stock pi install uses its own agent dir). Each line is a JSON object. Tool calls appear as assistant messages whose content carries tool-call entries: a tool name (e.g. `Bash`, `mcp__slack__slack_read_thread`) and, for a shell tool, the command string in its input.
+1. **Locate transcripts.** One Code / pi session transcripts live under the agent state dir at `~/.onecode/agent/sessions/<sanitized-cwd>/*.jsonl` (the bundled app's agent dir is `~/.onecode/agent`, or `ONECODE_AGENT_DIR` when set; a stock pi install uses its own agent dir, `PI_CODING_AGENT_DIR` or `~/.pi/agent`). Each line is a JSON object. Tool calls appear as assistant messages whose content carries tool-call entries: a tool name (e.g. `Bash`, `mcp__slack__slack_read_thread`) and, for a shell tool, the command string in its input.
 
    Scan the recent transcripts across the sessions dir — not just the current project — so the allowlist reflects your actual usage. Cap the scan at a reasonable number of recent sessions (e.g. 50 most-recently-modified JSONL files) so this stays fast.
 

package/skills/loop/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: loop
+description: Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.
+when_to_use: 'When the user wants to set up a recurring task, poll for status, or run something repeatedly on an interval (e.g. "check the deploy every 5 minutes", "keep running /babysit-prs"). Do NOT invoke for one-off tasks.'
+argument-hint: "[interval] [prompt]"
+---
+
+One Code builds this skill's instructions from its arguments when it runs
+(`extensions/background/loop-skill.ts`, Claude Code's `/loop`). This text shows
+only when the background extension is not loaded: tell the user `/loop` needs
+it, and do not schedule anything.