x9-task-graph

x9-task-graph is a skill for Claude Code, Codex from xonika9/agent-skills. It costs 93 tokens per session (543 once invoked), scanned A, original, MIT.

A planning tool that turns an approved implementation plan into connected work items with dependencies. A dependency shows which task must be completed before another can start.

In plain words
What is it for?
Use it to break a ready, approved plan into reviewable vertical tasks and arrange those tasks into a dependency-aware work graph.
Why use it?
It prevents unfinished, contradictory, or unapproved ideas from being treated as implementation tasks. It keeps the resulting work tied to the accepted plan.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Part of the x9-agent-skills plugin — 18 skills 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/xonika9/agent-skills/x9-task-graph
Any agent
npx skills add xonika9/agent-skills --skill x9-task-graph
Clone the repo
git clone --depth 1 https://github.com/xonika9/agent-skills

Made for: Claude Code, Codex.

Or install x9-agent-skills, the plugin that ships this one along with the rest of its 18 skills.

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 x9-task-graph

README.md
[![agentmods](https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-task-graph.svg)](https://agentmods.dev/skills/xonika9/agent-skills/x9-task-graph)
Your own site
<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-task-graph"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-task-graph.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 543 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 5.1 $0.00093 $0.00543
Opus 5 $0.00046 $0.00271
Sonnet 5 $0.00019 $0.00109
Haiku 4.5 $0.00009 $0.00054

Measured 6d ago against content hash aacc313d5e7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

x9-task-graph 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 6d 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/x9-task-graph/SKILL.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task graph

Turn an approved implementation plan into a complete, reviewable draft of connected vertical work items. This skill is model-invoked in Claude Code and Codex; its portable claim is structural Agent Skills compatibility only. Evidence tier: static.

Accept only a settled plan

Read the supplied artifact completely before deriving work. Approval means an explicit marker in the artifact or the user's confirmation in the current thread. Accept ce-unified-plan/v1 only when it is approved and its readiness is implementation-ready. Accept an equivalent plan only when it is approved and has a goal, requirements, decisions, implementation or work units, and verification.

Stop before decomposition when the input is unreadable, contradictory, partial, draft, or unapproved. Identify the exact missing, conflicting, or unapproved part and ask for the accepted version. A raw idea or request to choose product direction belongs to planning, not this skill.

Do not redesign the product, reopen accepted decisions, add requirements, invent implementation work, or implement the resulting items. Trace the approved source; an ambiguity that changes its meaning is a blocker rather than an invitation to replan.

Derive the draft

Read the work-item contract before deriving the graph. It owns work-item shape, vertical slicing, dependency/frontier semantics, tracker-ready representation, and the complete coverage matrix.

Use the plan's identifiers and wording where possible. Make dependencies only from accepted source constraints. A source-unit split or merge is allowed only when the coverage matrix explains why traceability remains complete.

Return the draft in chat by default. Read the publication boundary only when the user asks to save locally or publish externally; it owns all local-write and external-mutation gates, correlation, preview, retry, and reconciliation rules.

Done

For a valid source, completion is a chat draft that satisfies the work-item contract and whose coverage matrix accounts for every known requirement, decision, and source work unit. For refused input or gated mutation, completion is the named status and the exact missing authority, source evidence, or interface capability. Static validation does not prove live tracker publication or reconciliation.

Read the full file on GitHub · 29 lines

Files

What ships with it

2 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. 6d ago First seen · 29 lines · 93 tokens per session scan A aacc313d5e7c

Subscribe to this mod's changes

x9-task-graph is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 543 once invoked, about $0.0005 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

agentflow

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

sickn33/agentic-awesome-skills · 52 tokens

ai-dev-jobs-mcp

Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.

sickn33/agentic-awesome-skills · 41 tokens

asana-automation

Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.

sickn33/agentic-awesome-skills · 37 tokens

acceptance-orchestrator

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

sickn33/agentic-awesome-skills · 37 tokens

create-github-issue

Create GitHub issues using GitHub CLI with support for templates, labels, assignees, milestones, and draft issues. Use when the user asks to create a GitHub issue, file a bug report, submit a feature request, or open an issue in a GitHub repository.

tailcallhq/forgecode · 63 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens