task-graph-repair

task-graph-repair is a skill for Claude Code, Codex from Oortonaut/task-graph-mcp. It costs 33 tokens per session (2,084 once invoked), scanned A, original, Apache-2.0.

A set of repair steps for a task graph, which is a system that organizes work, dependencies, and agent ownership. It finds and fixes misplaced tasks, broken links between tasks, outdated claims, disconnected agents, and inconsistent data.

In plain words
What is it for?
Use it to inspect blocked or stale work, check agent status, find abandoned file claims, and repair task relationships and other data problems.
Why use it?
It helps restore a project plan when tasks are stuck, detached from their parent, assigned to inactive agents, or connected incorrectly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/oortonaut/task-graph-mcp/task-graph-repair
Any agent
npx skills add Oortonaut/task-graph-mcp --skill task-graph-repair
Clone the repo
git clone --depth 1 https://github.com/Oortonaut/task-graph-mcp

Made for: Claude Code, Codex.

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-graph-repair

README.md
[![agentmods](https://agentmods.dev/badge/skills/oortonaut/task-graph-mcp/task-graph-repair.svg)](https://agentmods.dev/skills/oortonaut/task-graph-mcp/task-graph-repair)
Your own site
<a href="https://agentmods.dev/skills/oortonaut/task-graph-mcp/task-graph-repair"><img src="https://agentmods.dev/badge/skills/oortonaut/task-graph-mcp/task-graph-repair.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,084 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 $0.00033 $0.02084
Opus 5 $0.00016 $0.01042
Sonnet 5 $0.00007 $0.00417
Haiku 4.5 $0.00003 $0.00208

Measured 5d ago against content hash 8149df61cee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

task-graph-repair 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 5d 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.

config/skills/task-graph-repair/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Graph Repair

Diagnose and fix common issues: orphaned tasks, broken dependencies, stale claims, disconnected agents, and data inconsistencies.

Prerequisite: Understand task-graph-basics for tool reference.


Quick Start

# 1. Connect with repair capabilities
connect(name="repair-agent", tags=["repair", "admin"])
→ agent_id

# 2. Run diagnostics
list_tasks(format="markdown")        # Overview
list_tasks(blocked=true)             # Blocked tasks
list_agents(format="markdown")       # Agent status

# 3. Fix issues as discovered
# (See specific repair procedures below)

Diagnostic Checklist

Run these queries to identify issues:

Query Looking For
list_tasks(blocked=true) Tasks stuck on deps
list_tasks(status="working") Potentially stale work
list_agents() Disconnected/stale agents
list_marks() Abandoned file marks
list_tasks(parent="null") Unexpected root tasks

Issue: Orphaned Tasks

Symptoms: Tasks with no parent that shouldn't be root tasks.

Diagnosis:

# Find all root tasks
list_tasks(parent="null")

# Identify which are intentional vs orphaned
# Orphaned = was child, parent deleted without cascade

Repair Options:

# Option A: Re-parent to correct parent
update(agent=agent_id, task=orphan_id, parent=correct_parent_id)

# Option B: Delete if no longer needed
delete(task=orphan_id, cascade=true)

# Option C: Make intentional root
# (No action needed, just document)

Issue: Broken Dependencies

Symptoms: Task blocked by non-existent task, or circular dependency.

Diagnosis:

# Find blocked tasks
list_tasks(blocked=true)

# For each, check blockers exist
get(task=blocked_task_id)  # Look at blockedBy field

# Try to fetch each blocker
get(task=blocker_id)  # Will fail if deleted

Repair:

# Remove reference to deleted blocker
unblock(blocker=deleted_task_id, blocked=stuck_task_id)

# For circular deps (rare, should be rejected):
# Break the cycle by removing one edge
unblock(blocker=task_a, blocked=task_b)

Read the full file on GitHub · 382 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. 5d ago First seen · 382 lines · 33 tokens per session scan A 8149df61cee0

Subscribe to this mod's changes

task-graph-repair is a skill published in the GitHub repository Oortonaut/task-graph-mcp (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,084 once invoked, about $0.0002 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens