coding-review

A read-only skill for auditing a local code diff or supplied implementation for defects that could affect production. It examines areas such as data loss, authorization, concurrency, compatibility, resilience, performance, and testing.

In plain words
What is it for?
Use it to inspect code changes, trace their effects through callers and data flows, and report actionable defects with the conditions that trigger them.
Why use it?
It focuses review on concrete problems that can change how software behaves, rather than producing general comments or making changes itself.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/evoelsewhere/evoflux/coding-review
Any agent
npx skills add evoelsewhere/evoflux --skill coding-review
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.00869
Opus 5 $0.00033 $0.00434
Sonnet 5 $0.00013 $0.00174
Haiku 4.5 $0.00007 $0.00087

Measured 2d ago against content hash 7c07cae3dbf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

app/agent/builtin_skills/coding-review/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a code change

Remain read-only unless the user separately authorizes fixes. Optimize for defects that change production behavior, not commentary volume. Do not load bundled references when this skill activates.

Establish intent and scope

  1. Determine the intended contract from the request, specification, tests, and existing behavior.
  2. Inspect the complete diff, including generated/configuration changes, then read enough surrounding code to understand every changed state transition and public boundary.
  3. Trace affected producers, callers, consumers, persistence, asynchronous work, and independently deployed dependents where behavior can propagate.

When a changed behavior cannot yet be tied to an exact declaration, call code_context with action="search" once with a stable changed literal, interface term, or code fragment. Use the result only to select an exact symbol; skip search when the diff already names it.

For exact changed symbols, use code_context to verify direct callers/references, outbound callees, and bounded impact rather than guessing propagation from filenames. Start at depth 1, disambiguate duplicate definitions, preserve repository labels, and reuse returned call-site source. Once a changed symbol and propagation question are selected, make the graph the next structural observation rather than continuing broad discovery.

Keep refresh=true for the first indexed query and after edits. Use refresh=false only for an immediate follow-up that intentionally reuses the same index version.

Read references/code-context-contract.md only when a result exposes limitations or truncation in cross-repository edges, dynamic wiring, or truncation that limits review coverage.

Review by risk

Check in this order:

  1. Incorrect result, lost or duplicated data, invalid state transition
  2. Authorization, tenant isolation, unsafe input, and secret exposure
  3. Concurrency, cancellation, retry, idempotency, and partial failure
  4. API, schema, serialization, configuration, and rollout compatibility
  5. Resource exhaustion, latency regression, and unbounded work
  6. Missing tests for changed behavior and failure modes

Read the full file on GitHub · 86 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 86 lines · 66 tokens per session scan A 7c07cae3dbf7

Subscribe to this mod's changes

coding-review is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 66 tokens to every session and 869 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

kane-cli

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…

LambdaTest/kane-cli · 159 tokens

rove

Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.

Sma1lboy/rove · 56 tokens

E2E Testing Nori Skillsets Subcommands

Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation.

tilework-tech/nori-skillsets · 39 tokens

release

Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI…

Sma1lboy/rove · 155 tokens

hyperframes-cli

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, or remove-background, or when troubleshooting the…

Sma1lboy/rove · 101 tokens

changelog-generator

Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…

Sma1lboy/rove · 101 tokens