task-review

task-review is a skill for Claude Code, Codex from SSBun/csl-agent-kit. It costs 60 tokens per session (674 once invoked), scanned A, original, MIT.

A read-only review process for one supplied result, task, file, configuration, design, or code change. It returns evidence-based feedback without editing the reviewed work.

In plain words
What is it for?
Use it for an explicit review of a pull request, diff, file, design, configuration, or other defined result.
Why use it?
It provides a focused second check while keeping the reviewed material unchanged. The review can identify issues without automatically applying fixes.

Skill for Claude CodeCodex

Part of the csl plugin — 33 skills, 2 commands, 5 agents, 10 hooks shipped together

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/ssbun/csl-agent-kit/task-review
Any agent
npx skills add SSBun/csl-agent-kit --skill task-review
Clone the repo
git clone --depth 1 https://github.com/SSBun/csl-agent-kit

Made for: Claude Code, Codex.

Or install csl, the plugin that ships this one along with the rest of its 33 skills, 2 commands, 5 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for task-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/task-review.svg)](https://agentmods.dev/skills/ssbun/csl-agent-kit/task-review)
Your own site
<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/task-review"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/task-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 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 $0.00060 $0.00674
Opus 5 $0.00030 $0.00337
Sonnet 5 $0.00012 $0.00135
Haiku 4.5 $0.00006 $0.00067

Measured 4d ago against content hash 056cbd4b8bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 4d 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.

skills/meta/task-review/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Review

Run one evidence-based review pass without changing the reviewed work.

Contract

  • Never infer review from risk, task state, or another workflow.
  • Return feedback only: no edits, task-state changes, reports, remediation, re-review, or approval.
  • Review any task state as its snapshot; explicit unfinished work is not a defect.
  • Route Reviewer–Editor remediation or approval to adversarial-review, and whole-subject audits elsewhere.

Workflow

  1. Target priority: named task; focused or owning task; supplied artifact or result; PR/MR, diff, or fixed point. Ask only if absent. See Review Workflow for Git details.
  2. Give the Reviewer the request/criteria, applicable Target/Result/Verification, result and diff, rules or spec, checks, and limitations. Exclude the author's defense, preferred conclusion, and proposed answer.
  3. Use exactly one fresh, read-only subagent when possible. It may inspect evidence and run non-destructive checks, but must not edit, change task state, or delegate. Never launch a nested host CLI.
  4. If unavailable or failed, run the same pass inline and label Review mode: non-independent self-review; otherwise label Review mode: independent subagent.
  5. Return feedback in the user's language and stop.

Lenses

  • Code: behavior, callers, edges, regressions, safety, compatibility, tests, and maintainability.
  • Documents and designs: claims, requirements, consistency, feasibility, failure modes, and validation.
  • Configuration and assets: behavior, compatibility, defaults, consumers, and validation.
  • No-file results: compare the claimed Result and evidence with the request or task Target.

Read only enough surrounding context to prove an issue; do not expand into an unrelated audit.

Findings

  • Critical Findings: demonstrated target failure or material correctness, security, privacy, data-integrity, regression, or compatibility harm.
  • Concerns: demonstrated non-critical problems with concrete impact.
  • Unverified Risks: material uncertainty from missing evidence or checks; not confirmed findings.

Read the full file on GitHub · 56 lines

Files

What ships with it

7 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. 4d ago First seen · 56 lines · 60 tokens per session scan A 056cbd4b8bd3

Subscribe to this mod's changes

task-review is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 674 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens