f-inspect
/f-inspect
Przegląda zakres commitów zadania przez wyspecjalizowanych agentów, zwraca tylko sprawdzone ustalenia, bez poprawek i werdyktu.
- Repozytorium
- toppingout ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 13.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 8
- Skrypty
- 7
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 7 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: loose-ends/detect.mjs, loose-ends/ignore.mjs, loose-ends/loose-ends.mjs, loose-ends/loose-ends.test.mjs, loose-ends/python.mjs, loose-ends/reuse.mjs, loose-ends/tests.mjs
Co robi i kiedy
Przegląda zakres commitów zadania przez wyspecjalizowanych agentów, zwraca tylko sprawdzone ustalenia, bez poprawek i werdyktu.
Wyzwalacze z opisu
Argumenty
/f-inspect <base sha>..<final head sha> [worktree]
Oryginalny opis (EN)
The foreman's lens inspection: review a finished job's commit range (base to final head, in its worktree) through fresh specialist lens agents and return evidence-checked findings only. Use when the owner or METHOD §8 says "run the lens inspection", /f-inspect, or after gate 2 on a STANDARD or FULL job. No PR exists yet and none is needed: this runs before the PR is prepared. Never fixes, never gives a verdict, never commits or pushes. Not the independent inspection (pack-review → xreview → adjudicate), not a review of an open PR (f-greploop). Also answers to its old name, /f-lens.
Jak działa
- 1 · Pin the scope
- 2 · Pick the lenses
- 3 · Brief every lens the same way
- 4 · Merge the findings
- 5 · Then
- Output
Podgląd SKILL.md
--- name: f-inspect description: > The foreman's lens inspection: review a finished job's commit range (base to final head, in its worktree) through fresh specialist lens agents and return evidence-checked findings only. Use when the owner or METHOD §8 says "run the lens inspection", /f-inspect, or after gate 2 on a STANDARD or FULL job. No PR exists yet and none is needed: this runs before the PR is prepared. Never fixes, never gives a verdict, never commits or pushes. Not the independent inspection (pack-review → xreview → adjudicate), not a review of an open PR (f-greploop). Also answers to its old name, /f-lens. argument-hint: "<base sha>..<final head sha> [worktree]" allowed-tools: ["Bash", "Glob", "Grep", "Read", "Task"] --- # Topping Out: Lens inspection The first of a job's two inspections (`METHOD.md` §8 step 3). The foreman runs it **in its own session**, after gate 2, over the job's finished work. **There is no PR yet**: the PR is prepared only after both inspections, the final re-run and the acceptance ledger. The builder never runs this and never reviews its own branch. **QUICK jobs skip it** (the record says `lens inspection: SKIP (QUICK)`). Topping Out's rules are built in: the scope is always the job's range, the mode is always findings-only. ## 1 · Pin the scope **First, the job file:** `ls foreman/jobs/JOB_*_<slug>.md` must list exactly one file. None means this isn't a job yet (`RULES.md` rule 15): **stop** and say so; the job starts with work order 1, which writes it. A late job file needs the owner's word and states its gaps. The scope is the job's commit range in its worktree, from the job record's header: ```bash WT="<worktree>"; BASE="<base sha>"; HEAD_SHA="<final head sha>" git -C "$WT" rev-parse HEAD # must equal $HEAD_SHA: stop if not git -C "$WT" status --short # only the profile's dirty-file allowlist git -C "$WT" diff --name-status "$BASE..$HEAD_SHA" # the manifest the lenses review git -C "$WT" diff "$BASE..$HEAD_SHA" > "<day folder>/lens/<ticket>.diff" ``` A wrong HEAD or an unexpected dirty file: **stop** and report it; don't review a moving target. Never check out, stash or reset anything. ## 2 · Pick the lenses Each triggered lens runs as a **fresh subagent** with no context from this job. Record which ran and which were skipped, with the reason. | Lens | Runs when | |---|---| | `lens-code` | always | | `lens-tests` | tests changed, or changed behaviour lacks a test | | `lens-errors` | error handling, fallbacks, catches or partial-failure paths changed | | `lens-types` | types, schemas or invariants changed | | `lens-comments` | durable comments or documentation prose changed | | `lens-instructions` | skills, agents, prompts or templates changed | | `lens-migrations` | the diff touches the repo profile's **database change paths** | | `lens-loose-ends` | the diff adds functions or edits existing code (nearly every job): it reads the rest of the repo for the copies, sibling lines and companion pieces the change should also have touched. Its script is `loose-ends/loose-ends.mjs` in this skill's folder; give the lens that path | | `lens-simplify` | last, and always with the words **report-only** (its no-write branch) | ## 3 · Brief every lens the same way - the range `<base>..<final head>`, the worktree path and the diff file; - the ticket's goal and its constraints, verbatim; - the settled decisions (`D-…`) marked **not to relitigate**; - one standing question: **where a test proves something is absent (no raw amount, no secret), is there also a test that pins the exact value shown?** Absence tests pass while the shown value is wrong; - **findings only**: no edits, no fixes, no verdict, no commit, no push, no PR; - **no test suites, builds or servers**: a lens reads the code and the diff; a finding that needs a run says so, and the foreman runs it on its own schedule (one test run at a time). The one exception is `lens-loose-ends`'s candidate script, a read-only lookup over git that runs nothing of the product. Lenses run sequentially by default. A lens never dispatches another lens and never touches git history. ## 4 · Merge the findings Every finding carries severity, confidence, file:line, the scenario, why it matters and the concrete remedy. The foreman: - de-duplicates and drops any finding it disproves against the code at the pinned head, noting the evidence; - reports a lens that halted, errored or returned `BLOCK` **as such**, never as a clean lens with zero findings; - keeps each lens's own severity words (no verdict mapping: this skill has no verdict). Write them to `templates/LENS-INSPECTION.md`'s findings table (`<day folder>/JOB-<N>-LENS-INSPECTION.md`). ## 5 · Then The findings go to adjudication (`templates/ADJUDICATION.md`): each one reproduced against the code, then accepted, rejected or partly accepted. Accepted findings become the builder's test-first repair work orders. This skill fixes nothing itself. ## Output Scope (range, pinned head, manifest), lenses run and skipped with reasons, ordered findings, any halted lens, remaining risks. **Never** a SHIP / BLOCK verdict, a fix, a commit, a push or a PR.
Pliki w paczce (8)
- SKILL.md 5 KB
- loose-ends/detect.mjs 9 KB
- loose-ends/ignore.mjs 2 KB
- loose-ends/loose-ends.mjs 14 KB
- loose-ends/loose-ends.test.mjs 4 KB
- loose-ends/python.mjs 4 KB
- loose-ends/reuse.mjs 6 KB
- loose-ends/tests.mjs 5 KB
Wersje
W bazie nie ma innych skilli o nazwie f-inspect.
Migawka bazy z 13.11.2026 · wersja paczki 859f3615f01a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 90xreview
Przegląda niezależnie wklejony PR, diff lub plan z innej sesji i oddaje tabelę twierdzeń, bez przepisywania kodu. - 100review
Przegląda wybrany obszar projektu przez wybraną soczewkę, a potem zamienia ustalenia w zadania naprawcze i propozycje bramek CI. - 100lens-review
Przegląda zmiany, diff gałęzi lub pull request kilkoma niezależnymi przeglądami, każdym w osobnym agencie, i zwraca jeden raport. - 100review-pr
Przegląda otwarty PR agentami z osobnym kontekstem, po jednym na soczewkę, weryfikuje każde ustalenie drugim agentem i naprawia to, co się broni. - 100review
Przegląda diff, gałąź, PR lub zakończone zgłoszenie pod kątem błędów przed scaleniem, raportując tylko ustalenia z dowodami. - 95ddd.xreview
Zleca równoległą recenzję kodu i dokumentów kilku niezależnym modelom AI, porównuje ustalenia i proponuje poprawki przed commitem.