review-code
Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own co
Install
npx skills add https://github.com/gtrabanco/agentic-workflow/tree/main/skills/review-code
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install gtrabanco-agentic-workflow@llmmart
git clone https://github.com/gtrabanco/agentic-workflow.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole gtrabanco/agentic-workflow collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Review Code (internal)
Composed by review-change / product-audit within their conversation — on any
agent, follow this file inline as the routed step. Findings only; never edits,
never refactors. Questions an unclear expectation raises obey the all-stages
no-assumption rule — ask-don't-infer, owner
skills/unit-lane/references/DESIGN.md (ask-dont-infer@1).
Scope
The diff or path/glob the caller passes; default the current change vs the default branch. State the scope at the top of the returned table.
Checklist (evaluate EVERY item — none is optional; n/a must be stated)
✓ No logic errors on the changed paths (trace each modified function's inputs →
outputs, including boundary values)
✓ Every error path is handled — no swallowed exceptions, no empty catch, no
silently-ignored return codes
✓ No duplicated logic (a changed block does not re-implement an existing
helper — cite the existing one if it does), including a shadow copy: a
file, schema, helper or prose block whose original lives outside the reviewed
tree, in a pinned dependency or a published package, is a duplicate of that
artifact — cite the artifact and its pin, or the recorded reason the copy must
exist; the vendoring rule demands provenance, never a second implementation
✓ No dead code introduced (unused functions, params, imports, unreachable
branches)
✓ No leftover TODO/FIXME/HACK markers in the diff
✓ Naming and file conventions match the project's docs (read them first; cite
the convention violated)
✓ No new abstraction beyond what the SPEC requires (an interface/base class
with one implementation is a finding)
✓ No new dependency not justified in the SPEC
✓ Simplification: any changed block that can lose lines without losing
behavior (cite before/after)
✓ Reference trace: every changed symbol/API got a reference search —
un-updated callers are findings
✓ Sweep declaration present: a changed token- or claim-shaped surface (a
published vocabulary token, a claim kind, a phrase a surface asserted, a
reader/echo pattern) carries its swept: /<pattern>/<flags> → expected <n> in <glob> line on the fold's ## Log entry — class workflow, the project's
own survivors rule, and scripts/promise-coherence.mjs re-runs it as
sweep-mismatch
✓ Edge cases the SPEC's dev scenarios name are actually handled in code, not
just in tests
✓ Is deleting the surface the complete fix? (S8) — before any edit is
proposed, check: does removing the surface entirely achieve the goal more
reliably than repairing it? If yes → route fix-now (delete), not
fix-now (repair). This is the deletion mandate: design and plan produce
retirements as first-class deliverables.
✓ Unused code routes two ways (#340) — every unconsumed symbol (or
unreferenced prose block) is a deletion candidate routed through the
classifier's two-way rule (review-implementation, CLASSIFY.md):
delivered-feature-without-consumer → bug finding; orphaned by a requested
replacement/removal → fix-now (delete). The row cites what requested the
feature and what replaced it — the two classes are never conflated
✓ Duplication is a deletion candidate (#340) — a duplicated block,
checklist or contract (code or prose) proposes its own deletion, or carries
the recorded reason the copy must exist; a silent duplicate is a finding
✓ Obsolete by an available mechanism is a deletion, code and docs (#353) —
a changed or neighbouring surface the project already supersedes (a helper a
pinned dependency owns, a doc describing a replaced flow, a local script the
runner provides) is fix-now (delete); the deciding rule is the project's
compatibility policy, read from its AGENTS.md before classifying — when
nothing in it requires keeping the old surface, keeping it is the finding and
deleting it is the fix
✓ A citation is not a consumer (#353) — prose (AGENTS.md, a skill, a
comment, a docs page) naming a symbol, file or block never makes it used; the
consumer test is executable or explicitly declared, and every citation is part
of what the deletion removes
✓ Features-preserved-without-it (#340) — after any proposed deletion
(code or skill prose; "code" includes prose), verify every requested
feature still works without the removed part before merge; a deletion that
breaks a requested feature is a finding, not a cleanup
✓ Removal-feature cascade (#340) — a change whose purpose is to remove a
feature deletes the code and its documentation and every sibling
mention the context makes necessary, with one sweep declaration per deleted
truth (swept: /<pattern>/<flags> → expected <n> in <glob>); when the
cascade's extent is unclear, the reviewer researches, understands and
contrasts — it does not guess the cascade's extent
Materiality bar
Report a row only when a competent user's outcome changes or a rule the project
explicitly declares is violated — cite the rule it violates beside the evidence.
Not findings: comment/punctuation typos, formatting-only drift, style preference
with no cited rule, hypothetical robustness beyond the SPEC's named scenarios.
An empty table with Decision: PASS is the expected result for a well-formed
change — never pad the table.
Return exactly
Sev and Impact are the two published closed sets (BLOCKER | CRITICAL | WARNING | SUGGESTION and blocking | docs-only | report-only); their meanings
are owned by review-implementation (CLASSIFY.md §Severity ladder) — assign a
token, never a prose grade.
REVIEW CODE — scope: <scope>
| # | Finding | Sev | Impact | Evidence | Suggested fix |
|---|---------|-----|--------|----------|---------------|
| 1 | <what> | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | <file:line> | <smallest action> |
Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)
Summary: <1-2 sentences>
Decision: PASS | FAIL
FAIL if any BLOCKER, CRITICAL or WARNING finding is open; PASS otherwise.
SUGGESTION findings never block — they route to the caller's triage step.
Done when
- Every checklist item was evaluated with evidence (file:line or command output) or explicitly marked n/a with the reason.
- The fixed-format block above is returned — nothing more, nothing less — and no code was changed.
Files (agentic-workflow)
-
SKILL.md 6.8 KB
--- name: review-code user-invocable: false version: 4.10.0 author: "Gabriel Trabanco <1969593+gtrabanco@users.noreply.github.com>" license: MIT description: > Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own conventions. Findings only; never edits code. --- # Review Code (internal) Composed by `review-change` / `product-audit` within their conversation — on any agent, follow this file inline as the routed step. **Findings only; never edits, never refactors.** Questions an unclear expectation raises obey the all-stages no-assumption rule — **ask-don't-infer**, owner `skills/unit-lane/references/DESIGN.md` (`ask-dont-infer@1`). ## Scope The diff or path/glob the caller passes; default the current change vs the default branch. State the scope at the top of the returned table. ## Checklist (evaluate EVERY item — none is optional; n/a must be stated) ✓ No logic errors on the changed paths (trace each modified function's inputs → outputs, including boundary values) ✓ Every error path is handled — no swallowed exceptions, no empty catch, no silently-ignored return codes ✓ No duplicated logic (a changed block does not re-implement an existing helper — cite the existing one if it does), **including a shadow copy**: a file, schema, helper or prose block whose original lives outside the reviewed tree, in a pinned dependency or a published package, is a duplicate of that artifact — cite the artifact and its pin, or the recorded reason the copy must exist; the vendoring rule demands provenance, never a second implementation ✓ No dead code introduced (unused functions, params, imports, unreachable branches) ✓ No leftover TODO/FIXME/HACK markers in the diff ✓ Naming and file conventions match the project's docs (read them first; cite the convention violated) ✓ No new abstraction beyond what the SPEC requires (an interface/base class with one implementation is a finding) ✓ No new dependency not justified in the SPEC ✓ Simplification: any changed block that can lose lines without losing behavior (cite before/after) ✓ Reference trace: every changed symbol/API got a reference search — un-updated callers are findings ✓ Sweep declaration present: a changed token- or claim-shaped surface (a published vocabulary token, a claim kind, a phrase a surface asserted, a reader/echo pattern) carries its `swept: /<pattern>/<flags> → expected <n> in <glob>` line on the fold's `## Log` entry — class `workflow`, the project's own survivors rule, and `scripts/promise-coherence.mjs` re-runs it as `sweep-mismatch` ✓ Edge cases the SPEC's dev scenarios name are actually handled in code, not just in tests ✓ **Is deleting the surface the complete fix? (S8)** — before any edit is proposed, check: does removing the surface entirely achieve the goal more reliably than repairing it? If yes → route `fix-now (delete)`, not `fix-now (repair)`. This is the deletion mandate: design and plan produce retirements as first-class deliverables. ✓ **Unused code routes two ways (#340)** — every unconsumed symbol (or unreferenced prose block) is a deletion candidate routed through the classifier's two-way rule (`review-implementation`, `CLASSIFY.md`): delivered-feature-without-consumer → bug finding; orphaned by a requested replacement/removal → `fix-now (delete)`. The row cites what requested the feature and what replaced it — the two classes are never conflated ✓ **Duplication is a deletion candidate (#340)** — a duplicated block, checklist or contract (code or prose) proposes its own deletion, or carries the recorded reason the copy must exist; a silent duplicate is a finding ✓ **Obsolete by an available mechanism is a deletion, code and docs (#353)** — a changed or neighbouring surface the project already supersedes (a helper a pinned dependency owns, a doc describing a replaced flow, a local script the runner provides) is `fix-now (delete)`; the deciding rule is the project's **compatibility policy**, read from its `AGENTS.md` before classifying — when nothing in it requires keeping the old surface, keeping it is the finding and deleting it is the fix ✓ **A citation is not a consumer (#353)** — prose (`AGENTS.md`, a skill, a comment, a docs page) naming a symbol, file or block never makes it used; the consumer test is executable or explicitly declared, and every citation is part of what the deletion removes ✓ **Features-preserved-without-it (#340)** — after any proposed deletion (code or skill prose; "code" includes prose), verify every requested feature still works without the removed part before merge; a deletion that breaks a requested feature is a finding, not a cleanup ✓ **Removal-feature cascade (#340)** — a change whose purpose is to remove a feature deletes the code **and** its documentation **and** every sibling mention the context makes necessary, with one sweep declaration per deleted truth (`swept: /<pattern>/<flags> → expected <n> in <glob>`); when the cascade's extent is unclear, the reviewer researches, understands and contrasts — it does not guess the cascade's extent ## Materiality bar Report a row only when a competent user's outcome changes or a rule the project explicitly declares is violated — cite the rule it violates beside the evidence. Not findings: comment/punctuation typos, formatting-only drift, style preference with no cited rule, hypothetical robustness beyond the SPEC's named scenarios. An empty table with `Decision: PASS` is the expected result for a well-formed change — never pad the table. ## Return exactly `Sev` and `Impact` are the two published closed sets (`BLOCKER | CRITICAL | WARNING | SUGGESTION` and `blocking | docs-only | report-only`); their meanings are owned by `review-implementation` (`CLASSIFY.md` §Severity ladder) — assign a token, never a prose grade. ``` REVIEW CODE — scope: <scope> | # | Finding | Sev | Impact | Evidence | Suggested fix | |---|---------|-----|--------|----------|---------------| | 1 | <what> | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | <file:line> | <smallest action> | Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>) Summary: <1-2 sentences> Decision: PASS | FAIL ``` FAIL if any `BLOCKER`, `CRITICAL` or `WARNING` finding is open; PASS otherwise. `SUGGESTION` findings never block — they route to the caller's triage step. ## Done when - Every checklist item was evaluated with evidence (file:line or command output) or explicitly marked n/a with the reason. - The fixed-format block above is returned — nothing more, nothing less — and no code was changed.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.