receiving-code-review
/receiving-code-review
Assess reviewer's suggested change (rename, refactor, move, extract) — query tea-rags imports/churn signals on affected target, measure blast radius before agreeing or pushing back. Triggers on "reviewer suggests", "should I rename", "ревьюер предлагает", "стоит ли переименовать", "code review feedback", "PR comment about", "review feedback says", "PR comment wants", "address the review", "сделай как просит ревьюер", "code review wants me to", "let's refactor this per review". NOT for vague stylistic nits without a named symbol. Wraps superpowers:receiving-code-review with tea-rags blast-radiu
- Author
- artk0de ↗
- Repository
- tearags-mcp ↗
- Licence
- MIT
- Last repository change
- 18.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 18.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Assess reviewer's suggested change (rename, refactor, move, extract) — query tea-rags imports/churn signals on affected target, measure blast radius before agreeing or pushing back. Triggers on "reviewer suggests", "should I rename", "ревьюер предлагает", "стоит ли переименовать", "code review feedback", "PR comment about", "review feedback says", "PR comment wants", "address the review", "сделай как просит ревьюер", "code review wants me to", "let's refactor this per review". NOT for vague stylistic nits without a named symbol. Wraps superpowers:receiving-code-review with tea-rags blast-radiu
Triggers from the description
Original author description
Assess reviewer's suggested change (rename, refactor, move, extract) — query tea-rags imports/churn signals on affected target, measure blast radius before agreeing or pushing back. Triggers on "reviewer suggests", "should I rename", "ревьюер предлагает", "стоит ли переименовать", "code review feedback", "PR comment about", "review feedback says", "PR comment wants", "address the review", "сделай как просит ревьюер", "code review wants me to", "let's refactor this per review". NOT for vague stylistic nits without a named symbol. Wraps superpowers:receiving-code-review with tea-rags blast-radiu
How it works
- Iron Rule
- Step 1 — Extract review target
- Step 2 — Impact analysis call
- Step 3 — Compute agreement verdict
- Step 3.5 — Trace the call route the change rides (optional, preferred when the comment nam
- Step 3a — Tests bound to the target
- Step 3b — Naming comments (codegraph on)
- Step 4 — Invoke superpowers:receiving-code-review
- Red Flags — STOP and restart from Step 2
- Common Mistakes
SKILL.md preview
---
name: receiving-code-review
description:
Assess reviewer's suggested change (rename, refactor, move, extract) — query
tea-rags imports/churn signals on affected target, measure blast radius before
agreeing or pushing back. Triggers on "reviewer suggests", "should I rename",
"ревьюер предлагает", "стоит ли переименовать", "code review feedback", "PR
comment about", "review feedback says", "PR comment wants", "address the
review", "сделай как просит ревьюер", "code review wants me to", "let's
refactor this per review". NOT for vague stylistic nits without a named
symbol. Wraps superpowers:receiving-code-review with tea-rags blast-radius
signals.
---
# dinopowers: receiving-code-review
Wrapper over `superpowers:receiving-code-review`. Agreement with review comment
backed by impact data — accepting this comment affects 3 callers or 300? — not
performative "yes" without verification.
## Iron Rule
**tea-rags impact analysis MUST run on the review-comment's target BEFORE
agreeing to implement** — whenever comment names concrete symbol or file.
Correct tool (`semantic_search`) + correct impact rerank (`blastRadius` / custom
fallback) (`imports: 0.5, churn: 0.3, ownership: 0.2`) + correct parameters
(pathPattern scoping to target, `metaOnly: true`) + ordering (analysis BEFORE
agreement) = core value.
Comment stylistic-only (typo, spacing): skip wrapper, pass through to
`superpowers:receiving-code-review`. Don't fabricate target. A naming comment
("rename X to Y", "unclear name") is never stylistic-only — it runs Step 3b.
**Chaining rule:** see [CHAINING.md](../../CHAINING.md) — every dinopowers:X
redirects superpowers:X. NEVER bypass wrapper.
**Index freshness:** see [FRESHNESS.md](../../FRESHNESS.md) and
`tea-rags/rules/index-freshness.md`. No background reindex hook. Linked
worktree: overlay serves uncommitted edits — never reindex for them. Main
checkout: incremental `mcp__tea-rags__index_codebase` BEFORE first tea-rags call
over code edited but not committed.
## Step 1 — Extract review target
From review comment identify:
| Element | Example |
| ------------------------------------------------------------- | ------------------------------------------------------ |
| **Target** — symbol or file the comment proposes changing | `ChunkGrouper.group()`, `src/core/contracts/errors.ts` |
| **Change type** — rename / refactor / move / extract / inline | "rename `group` to `aggregate`" |
| **Scope** — local (same file) vs cross-cutting | "rename exported symbol" = cross-cutting |
Compose:
- `targetPathPattern`: scoping pattern (e.g. `**/chunk-grouper.ts`, or broader
if cross-cutting)
- `intent`: one-sentence framing of proposed change
Comment stylistic-only: skip to Step 4 with verdict
`PASS-THROUGH (non-structural)`. Don't invent structural implications.
## Step 2 — Impact analysis call
Issue ONE `mcp__tea-rags__semantic_search` — SAME idiom as
`dinopowers:writing-plans` / `executing-plans` /
`verification-before-completion`:
```
path: <your working directory> ← tea-rags search-cascade "Addressing the Codebase"; never project alone
query: <intent from Step 1>
pathPattern: <targetPathPattern>
rerank: "blastRadius" ← codegraph on; else { custom: { imports: 0.5, churn: 0.3, ownership: 0.2 } }
limit: 10
metaOnly: true
```
Do NOT substitute:
| Wrong tool | Why wrong |
| -------------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| `mcp__tea-rags__hybrid_search` | Same rerank, but its BM25 leg re-ranks by query-token overlap — signal scan wants semantic + signals |
| Other named preset (`"hotspots"` / `"codeReview"`) | Named presets miss `imports` weight |
| `mcp__tea-rags__find_similar` on target | Finds structural analogs, not importers |
| `grep -rn "ChunkGrouper"` for usages | Misses the ranked `imports` overlay; noisy with comments/strings |
| `mcp__tree-sitter__trace_impact` as primary | Structural complement; this wrapper is git-first |
Do NOT pass:
- `metaOnly: false` — verdict inputs are signals, not content
- Different weights — must match project idiom
- `filter` narrowing — pathPattern already scopes
Results empty: verdict `UNVERIFIABLE (target not in index)`. Don't fabricate.
## Step 3 — Compute agreement verdict
Extract raw from payload (`imports` root, `git.file.commitCount`,
`git.file.blameDominantAuthor` live-line owner); labels + non-essential signals
(`bugFixRate`, `recentDominantAuthor` recent committer) from
`rankingOverlay.file.*` when the rerank surfaces them — metaOnly payload keeps
git essential fields only.
Verdict ladder:
| Verdict | Triggers | Action |
| ------------------ | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `AGREE-WITH-SCOPE` | imports > 20 OR bugFixRate > 30% | Agree, but expand scope: list all N importers in response + commit to update them OR explain why a partial change is acceptable |
| `AGREE-DIRECT` | imports ≤ 5 AND bugFixRate ≤ 20% | Agree; small blast radius; single-commit change |
| `PUSHBACK` | imports > 50 (massive blast) | Respond with impact data: "renaming X affects N modules across M authors — propose alternative or narrower change first" |
Compose response block:
```
### Impact analysis for review comment: "<comment>"
Target: <symbol or file>
- imports: <N> (rank <R> of <K> in targetPathPattern)
- churn: <N> commits, last touched <D> days ago
- live-line owner: <blameDominantAuthor> (<blameDominantAuthorPct>%)
- recent committer: <recentDominantAuthor> (<recentDominantAuthorPct>%)
- bugFixRate: <X%>
Verdict: <AGREE-WITH-SCOPE | AGREE-DIRECT | PUSHBACK>
```
## Step 3.5 — Trace the call route the change rides (optional, preferred when the comment names a call relationship)
Step 2 gives **single-symbol** blast-radius number — importer count of target.
When review comment names **relationship between two symbols** ("change how `X`
calls `Y`", "this method should not reach `Z`", "route this through `W`
instead"), change rides a **call route**, not one symbol. Promote single fanIn
to actual PATH: call `mcp__tea-rags__trace_path` between the two named endpoints
to SEE the route the change travels and which step is highest-impact chokepoint.
**Requires codegraph** (prime shows `codegraph.symbols`); when off, `trace_path`
not registered — stay with Step 2 single-symbol fanIn, note route view
unavailable.
```
mcp__tea-rags__trace_path(
from="<caller symbol the comment names>", # e.g. the X in "how X calls Y"
to="<callee symbol the comment names>", # e.g. the Y, or the Z it "should not reach"
rerank="blastRadius" # rank each hop by fanIn / import impact
)
```
Read the result like this:
- **`dangerRanking[0]`** — highest-impact step ON route, not necessarily either
endpoint. Chokepoint the proposed change ripples through. "What does this
change touch" becomes concrete hop with measured fanIn instead of one number
on named symbol.
- **`dangerOverlay`** per step — carries `imports` / churn for that hop, so a
quiet intermediate everything routes through surfaces instead of hiding
between the two named endpoints.
- **Empty result** — check `namesakes` first (wrong `fromPath`/`toPath` pin →
fix the pin), and the floor rule (no `codegraph` floor + `changedFiles` > 0 →
edges in changed files are the index's — re-check). Only then: NO static call
path from `from` to `to`; review comment's premise ("X reaches Y") may be
**structurally false** — useful pushback input: change targets a route that
doesn't exist as reviewer imagines. Confirm before agreeing.
Preset selection for the trace:
| Situation | `rerank` |
| ------------------------------------------------------------- | ------------- |
| "What does this change ripple through" — impact-ranked route | `blastRadius` |
| "Who else owns the steps I'd touch" — who to loop into the PR | `ownership` |
Use `rerank="ownership"` to see who owns each step on route — reviewer named two
symbols, but change rides hops owned by others who should be looped into review.
Bound search with `maxDepth` / `maxPaths` if graph deep or branchy.
Append traced route under impact block from Step 3:
```
**Call route the change rides (<from> → <to>), danger-ranked:**
- chokepoint: <dangerRanking[0] symbol> @ <file>:<line>
overlay: imports <N>, churn <Y>
- also on route: <next step> @ <file>:<line>
owner (ownership preset): <blameDominantAuthor> — loop into review
```
Result empty: append
`**Call route:** no static path <from> → <to> — the reviewer's "X reaches Y" premise may not hold; confirm before agreeing`.
Danger-ranked route makes "what does this change ripple through" concrete: a
chokepoint with measured fanIn and named owner is different conversation than a
single import count on the symbol reviewer happened to name.
## Step 3a — Tests bound to the target
When proposed change is rename / move / extract / signature change on a symbol,
tests bound to current name or signature must be identified BEFORE agreeing.
Invoke `Skill(tea-rags:tests-as-context)` with:
```
recipe: "tests-at-risk"
affectedFiles: [<file containing the target symbol>] ← single-element array OK
intent: <intent from Step 1, e.g. "rename ChunkGrouper.group to aggregate">
```
Recipe accepts single-element `affectedFiles` for symbol-scoped changes —
internally uses `must_not relativePath any-of` filter, works identically for one
or many paths.
Recipe surfaces DSL leaf test chunks exercising the affected symbol. Append to
impact block:
```
**Tests bound to current name/signature:**
- <file>:<line> — <describe-it path>
- <file>:<line> — <describe-it path>
```
Recipe returned SKIP: append
`**Tests bound:** unavailable (no DSL test chunks indexed)`. Recipe returned
empty list: append
`**Tests bound:** no obvious test bindings — the change may still affect untested paths`.
Bound-test list raises cost of proposed change visibly: agreeing to a rename
that breaks 6 named scenarios is different conversation than one with no test
bindings. Phrasing stays runner-agnostic — list scenarios, never name a runner.
## Step 3b — Naming comments (codegraph on)
Rename / "unclear name" comment →
`get_naming_lexicon(names=[{current}, {proposed}], language=<file's>, pathPattern=<targetPathPattern>)`
— evidence never crosses languages. Proposed `CONFORMS` → agree on the name
(unless it carries `alternatives` — the project's word for the same concept);
proposed `MISFIT` → counter-propose its `suggestion` (holder as precedent);
proposed `NEW_TERM` while current `CONFORMS` → push back with the project's
term.
Comment on naming across the whole change, no identifier named ("names in this
PR don't match the codebase") →
`review_changes(changes={ base: <the PR's target branch> }, sections: ["naming"])`
— one call over the names the diff adds (the tool reads the base at its
merge-base with HEAD); never hand-list them into `names[]`. Findings =
`review.findings`, each flat `{relPath, line, name, kind, type?, verdict, …}`.
Answer per finding: `MISFIT` → apply `suggestion` (a type MISFIT with
`role.evidence: "directory"` only when the type belongs to `role.examples`'
family — else push back: location, not name); `COLLISION` → rename or justify
against `existing`; `NEW_TERM` → keep with a justification or take an offered
`alternatives` word; `genericName` → generic name, rename or justify. Conforming
names stay; `review.novel` counts names with nothing to compare against — no
action. Append the verdicts to the impact block — the naming verdict decides
WHICH name, Step 2 decides the cost. Reading: `tea-rags:data-driven-generation`
Step 5 "Naming (lexicon)".
## Step 4 — Invoke superpowers:receiving-code-review
Invoke `Skill` tool with `superpowers:receiving-code-review`. Prepend impact
block as context. Phrase handoff as:
> "Before agreeing to this review, note impact signals: …<block>… Respond with
> agreement tied to scope, or respectful pushback if blast radius warrants it.
> Technical rigor, not performative agreement.
>
> Chaining rule reminder: when your cycle would next invoke
> `superpowers:verification-before-completion` (or any wrapped `superpowers:Y`),
> invoke `dinopowers:Y` instead — see the Chaining rule section above."
Let `superpowers:receiving-code-review` run standard rigorous-response cycle.
Wrapper informs whether agreement safe and at what scope.
## Red Flags — STOP and restart from Step 2
- "Comment is clear, I'll just do it" → if names symbol/file, run Step 2 anyway
- "It's just a rename" → renames propagate through imports; always analyze
- Substituted grep/git log → redo with semantic_search + Step 2 rerank
- Wrong rerank for codegraph state → redo: `"blastRadius"` when prime
`## Enrichment` lists `codegraph.symbols`, else
`{imports: 0.5, churn: 0.3, ownership: 0.2}` (tea-rags analytics-rerank)
- Agreed before Step 2 (performative yes) → revert, restart
- Pushed back before Step 2 (defensive no) → revert, restart
- Let `superpowers:receiving-code-review` chain into a raw
`superpowers:verification-before-completion` without redirecting to
`dinopowers:verification-before-completion` → intercept and invoke wrapper
instead (see Chaining rule)
## Common Mistakes
| Mistake | Reality |
| ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| Performative "good catch" agreement | Rigorous agreement requires impact data. Run Step 2. |
| Blanket pushback without evidence | Defensive no is as bad as performative yes. Data first. |
| Use `rerank: "codeReview"` preset because "this is code review" | codeReview preset is for finding reviewable code, not impact of a change |
| `find_similar` to assess rename blast radius | find_similar shows analogs, not callers. Use impact rerank. |
| Ignore `imports` when comment proposes a rename | Rename affects every importer. imports count = response effort |
| Agree then grep for callers during implementation | Wrong order — impact analysis informs whether to agree at all |
| Comment names "how X calls Y" but you only ran single-symbol Step 2 | The change rides a route. `trace_path(from=X, to=Y, rerank="blastRadius")` shows the chokepoint, not just one fanIn (Step 3.5) |
| Loop in only the symbol's owner when the change crosses a route | The hops between X and Y have other owners. `rerank="ownership"` on the route surfaces who else to loop in |
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · artk0de/tearags-mcp | 100 | MIT |
| event4u-app/agent-config | 100 | MIT |
| drvoss/everything-copilot-cli | 100 | MIT |
| rootcastleco/rei-skills | 100 | MIT |
| foryourhealth111-pixel/Vibe-Skills | 100 | Apache-2.0 |
| jjuraszek/pi-gauntlet | 100 | MIT |
| coco-research/coco | 100 | MIT |
| davila7/claude-code-templates | 100 | MIT |
| osmontero/opencode-skills | 100 | MIT |
Database snapshot: 13.11.2026 · package version f36d59085c9b (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100dino-receiving-code-review
Assess reviewer''s suggested change (rename, refactor, move, extract) — query tea-rags imports/churn signals on affected target, measure blast radius before agreeing or pushing back. Triggers on "reviewer suggests", "should I rename", "ревьюер предлагает", "стоит ли… - 100brainstorming
Brainstorm code change seeing risk, ownership, tech-debt signals from tea-rags first — creative exploration grounded in actual state of affected area. Triggers on "brainstorm X", "design feature", "refactor Y", "let's discuss", "давай обсудим", "как перестроить", "что может… - 100implementer-receiving-review-feedback
Use when receiving review findings, when a reviewer flagged an issue, during a review cycle, or when responding to review. Loads implementer-specific discipline that complements superpowers:receiving-code-review. - 100implementer-receiving-review-feedback
Use when receiving review findings, when a reviewer flagged an issue, during a review cycle, or when responding to review. Loads implementer-specific discipline that complements superpowers:receiving-code-review." # source:… - 100code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback… - 100code-reviewer
Use when reviewing pull requests or conducting code quality audits. Invoke for PR reviews, code quality checks, refactoring suggestions. For security audits use security-reviewer; for acting on received review feedback use receiving-code-review-sre; for infra change review…