task-orchestrator

task-orchestrator is a skill for Claude Code, Codex from Ohswedd/praxis. It costs 117 tokens per session (4,538 once invoked), scanned A, original, MIT.

A structured workflow for making code changes from a short request through specification, implementation, testing, and reporting.

In plain words
What is it for?
Use it when fixing, adding, integrating, refactoring, updating, migrating, or optimising a codebase.
Why use it?
It helps prevent missing requirements, unfinished error handling, untested edge cases, and claims that were not actually checked.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the praxis plugin — 15 skills, 8 commands, 13 agents, 5 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/ohswedd/praxis/task-orchestrator
Any agent
npx skills add Ohswedd/praxis --skill task-orchestrator
Clone the repo
git clone --depth 1 https://github.com/Ohswedd/praxis

Made for: Claude Code, Codex.

Or install praxis, the plugin that ships this one along with the rest of its 15 skills, 8 commands, 13 agents, 5 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-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohswedd/praxis/task-orchestrator.svg)](https://agentmods.dev/skills/ohswedd/praxis/task-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/ohswedd/praxis/task-orchestrator"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/task-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,538 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 $0.00117 $0.04538
Opus 5 $0.00059 $0.02269
Sonnet 5 $0.00023 $0.00908
Haiku 4.5 $0.00012 $0.00454

Measured 4d ago against content hash 97cafc796b09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-orchestrator 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.

plugins/praxis/skills/task-orchestrator/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Orchestrator

This is praxis's spine. It turns a terse request into a complete, production-ready change with nothing left implicit. Run the phases in order; do not skip ahead to editing. Prioritise correctness and completeness over speed.

The golden rule: nothing may be silently dropped, stubbed, or left out-of-scope. If something cannot be done, it is stated explicitly in the report, never hidden behind a placeholder.

"Out of scope / follow-ups" is for what the user excluded or what genuinely belongs to another change. It is not a place to move work you started and did not finish, and it is not a way to hand back a first pass. Everything the spec puts in scope, including the error paths, the empty and failure states, the validation, and the tests, ships in this change.

The second golden rule: state only what you verified. Every phase below produces claims (this passes, that is covered, the docs are updated), and a claim that turns out on a second look to be untrue costs more than the work it was meant to save, because it is believed. Run the command instead of predicting its output, read the file before citing it, and when something could not be checked, say so in the report. praxis measures what it can: report.py runs the tests, the runtime harness and the scanners itself, and refuses a vertical citation that does not resolve. What it cannot measure is on you.

Two house rules apply to every phase, and both are enforced deterministically, so they are not worth testing: no em dashes in anything you write (code, comments, docs, commit messages, or your reply to the user), and no AI attribution in the project's record. Use a colon, a comma, parentheses, or two sentences instead of the dash, and never add a co-author trailer or a "generated with" credit.


Phase 1: Restructure the request (spec)

Use the prompt-architect skill to convert the request into an explicit spec:

  • Goal: the outcome, in one or two sentences.
  • In scope: concrete deliverables.
  • Out of scope / non-goals: what you will deliberately not do (surface this; never narrow scope silently).
  • Acceptance criteria: testable conditions for "done".
  • Affected areas: files/subsystems likely touched (fill after Phase 2).
  • Assumptions: anything you inferred that the user did not state.
  • Open questions: genuine ambiguities. Ask them now if they block correct work; otherwise state the assumption you will proceed under.

Read the full file on GitHub · 345 lines

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 · 345 lines · 117 tokens per session scan A 97cafc796b09

Subscribe to this mod's changes

task-orchestrator is a skill published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 4,538 once invoked, about $0.0006 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

scroll-craft

Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…

nateherkai/scroll-craft · 177 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

wp-demo

Demo HTML creation methodology — single-file demos with section comments for 1:1 WordPress conversion.

yojahny55/claude-wp-builder · 22 tokens

wp-polylang

Polylang multilingual methodology — one post per language joined by translation groups, driven through the pll API.

yojahny55/claude-wp-builder · 26 tokens

wp-responsive

Responsive design patterns — mobile-first breakpoints, fluid typography, responsive images, touch targets.

yojahny55/claude-wp-builder · 20 tokens

wp-contributing

Contributing to the claude-wp-builder plugin itself — the four-layer architecture and what may call what, why tests are grep gates over prose, the frontmatter contract per layer, the two i18n systems, and the PR and release rituals. Use when editing this repository's own commands/, agents/, skills/, starter-theme/…

yojahny55/claude-wp-builder · 86 tokens