work-graph

A command that draws a dependency graph: a visual map showing which work items rely on others. It can display the map in the terminal or create Graphviz DOT and SVG files.

In plain words
What is it for?
Use it to inspect all or filtered work items, find the tasks that control the schedule, analyze bottlenecks, view statistics, or focus on one item’s nearby dependencies.
Why use it?
It makes blocked work, the critical path, and bottlenecks easier to see than a plain list of tasks.

Command

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 commands/ankushdixit/claude-plugins/work-graph
Clone the repo
git clone --depth 1 https://github.com/ankushdixit/claude-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 956 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 $0.00007 $0.00956
Opus 5 $0.00003 $0.00478
Sonnet 5 $0.00001 $0.00191
Haiku 4.5 $0.00001 $0.00096

Measured yesterday against content hash a5790b5b9955, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-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 yesterday.

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.

solokit/commands/work-graph.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Item Graph

Generate visual dependency graphs showing relationships between work items, with critical path highlighting and bottleneck analysis.

Usage

Ask the user what type of graph they want to generate:

  1. Format - Ask: "What output format would you like?"

    • Options: ascii (default, terminal display), dot (Graphviz), svg (requires Graphviz)
    • Default to ascii if not specified
  2. Filters - Ask: "Any filters to apply? (or 'none' for all work items)"

    • Status: only show items with specific status (not_started, in_progress, completed)
    • Milestone: only show items in specific milestone
    • Type: only show specific work item types
    • Include completed: whether to show completed items (default: no)
  3. Special views - Ask: "Need any special analysis?"

    • critical-path: Show only critical path items
    • bottlenecks: Highlight bottleneck analysis
    • stats: Show graph statistics
    • focus <work_item_id>: Show neighborhood of specific item

After Collecting Information

Run the appropriate command based on user input:

Basic usage:

sk work-graph

With format:

sk work-graph --format dot
sk work-graph --format svg --output graph.svg

With filters:

sk work-graph --status not_started
sk work-graph --milestone "Phase 3"
sk work-graph --type feature
sk work-graph --include-completed

Special views:

sk work-graph --critical-path
sk work-graph --bottlenecks
sk work-graph --stats
sk work-graph --focus feature_add_authentication

Combined filters:

sk work-graph --status not_started --milestone "Phase 3" --format svg --output phase3.svg

Output

The command will generate a visual graph showing:

  • Work items as nodes (with ID, title, status)
  • Dependencies as edges (arrows from dependency to dependent)
  • Critical path highlighted in red
  • Color coding by status and priority
  • Bottlenecks identified

Display the output to the user and explain key insights:

Read the full file on GitHub · 163 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. yesterday First seen · 163 lines · 0 tokens per session scan A a5790b5b9955

Subscribe to this mod's changes

work-graph is a command published in the GitHub repository ankushdixit/claude-plugins (3 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 956 once invoked, about $0.0000 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.