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.
git clone --depth 1 https://github.com/ankushdixit/claude-pluginsWrote 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.
[](https://agentmods.dev/commands/ankushdixit/claude-plugins/work-graph)<a href="https://agentmods.dev/commands/ankushdixit/claude-plugins/work-graph"><img src="https://agentmods.dev/badge/commands/ankushdixit/claude-plugins/work-graph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ankushdixit/claude-plugins/work-graph"><img src="https://agentmods.dev/badge/commands/ankushdixit/claude-plugins/work-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.00956 |
| Opus 5.5 | $0.00003 | $0.00382 |
| Sonnet 5.5 | $0.00001 | $0.00191 |
| Haiku 4.5 | $0.00001 | $0.00096 |
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 1mo 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.
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:
-
Format - Ask: "What output format would you like?"
- Options: ascii (default, terminal display), dot (Graphviz), svg (requires Graphviz)
- Default to ascii if not specified
-
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)
-
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:
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.
- 1mo ago First seen · 163 lines · 0 tokens per session scan A a5790b5b9955
work-graph is a command published in the GitHub repository ankushdixit/claude-plugins (3 stars, last pushed 9mo ago), licensed MIT. It adds 7 tokens to every session and 956 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.