review-tasks

A read-only backlog reviewer for todo kotgent tasks. A backlog is a list of planned or unfinished work, and kotgent is the task tracker used by these workflows.

In plain words
What is it for?
Use it to inspect the repository and task tracker, then recommend whether each task should stay, be rewritten, merged, dropped, or escalated.
Why use it?
It identifies tasks that are finished, outdated, duplicated, conflicting, absorbed into other work, or incorrectly blocked.

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/heapy/kortex/review-tasks
Any agent
npx skills add Heapy/kortex --skill review-tasks
Clone the repo
git clone --depth 1 https://github.com/Heapy/kortex

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 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 $0.00073 $0.00799
Opus 5 $0.00036 $0.00400
Sonnet 5 $0.00015 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 2d ago against content hash 102f1deb6a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-tasks 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.

plugins/kotgent/skills/review-tasks/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Tasks

Review only todo tasks and produce recommendations backed by repository evidence. Use the kotgent CLI for tracker reads and git plus ordinary file inspection for repository evidence. Do not use an MCP server, SDK, direct daemon request, or helper script.

Stay read-only

Do not add comments, change state, edit dependencies, delete tasks, initialize or restore projects, or edit repository files. In particular, do not run any mutating task or project subcommand.

Treat successful task and project stdout as JSON and failure stderr as JSON. Exit 2 is a command-construction error whose stderr may be plain usage text; stop and report the exact command and stderr. Do not retry a deleted-project error or restore/reinitialize a project.

Collect the review set

  1. Require git and kotgent, resolve the Git root, and read the root .kotgent.json. Stop if its project UUID is unavailable or invalid.
  2. Determine whether that exact UUID is live with kotgent project list or archived with kotgent project list --archived. An archived backlog may be reviewed read-only; label it clearly.
  3. Run kotgent task list --project <project-uuid>. Select only rows whose state is exactly todo. Other states may be comparison evidence, but never make them review candidates.
  4. Run kotgent task show <ref> for every todo row. When a blocked task depends on another ref, read that dependency's detail as needed to evaluate the edge.
  5. Record branch, full HEAD, and git status --short to identify the repository snapshot.

Test each todo task

Read applicable AGENTS.md and CLAUDE.md first, then active plans/backlogs, implementation, tests, relevant TODO/FIXME markers, uncommitted work, and focused Git history. Test each task for:

  • work already implemented and verified in code or history;
  • obsolete assumptions, APIs, product intent, or plans;
  • conflict with current architecture or repository rules;
  • duplicate scope with another active task;
  • scope absorbed by a broader task or completed change;
  • an incorrect blocker: the dependency is already satisfied, unrelated, reversed, or contradicted by current repository sequencing.

Read the full file on GitHub · 65 lines

Files

What ships with it

1 file 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 · 65 lines · 73 tokens per session scan A 102f1deb6a1d

Subscribe to this mod's changes

review-tasks is a skill published in the GitHub repository Heapy/kortex (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 799 once invoked, about $0.0004 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

add-azuredevops

Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.

microsoft/power-platform-skills · 37 tokens

37signals-way

Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…

wondelai/skills · 177 tokens

inspired-product

Build empowered product teams using discovery and delivery dual-track. Use when the user mentions "product discovery", "empowered teams", "feature factory", "opportunity assessment", "product vision", "product strategy", "what should we build", or "our roadmap is just a feature list". Also trigger when restructuring…

wondelai/skills · 119 tokens

skills-manager-cli

Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…

jiweiyeah/Skills-Manager · 151 tokens

issue-triage

Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.

decebals/claude-code-java · 44 tokens

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

oliver-kriska/claude-elixir-phoenix · 48 tokens