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.
npx agentmods add commands/sakrut/ai-code-graph/show-taskgit clone --depth 1 https://github.com/sakrut/ai-code-graphWhat 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 | $0.00000 | $0.00505 |
| Opus 5 | $0.00000 | $0.00253 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
show-task 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 2d 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.
This is a copy
97% identical to show-task — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Show Task
Arguments: $ARGUMENTS Show detailed task information with rich context and insights.
Arguments: $ARGUMENTS
Enhanced Task Display
Parse arguments to determine what to show and how.
1. Smart Task Selection
Based on $ARGUMENTS:
- Number → Show specific task with full context
- "current" → Show active in-progress task(s)
- "next" → Show recommended next task
- "blocked" → Show all blocked tasks with reasons
- "critical" → Show critical path tasks
- Multiple IDs → Comparative view
2. Contextual Information
For each task, intelligently include:
Core Details
- Full task information (id, title, description, details)
- Current status with history
- Test strategy and acceptance criteria
- Priority and complexity analysis
Relationships
- Dependencies (what it needs)
- Dependents (what needs it)
- Parent/subtask hierarchy
- Related tasks (similar work)
Time Intelligence
- Created/updated timestamps
- Time in current status
- Estimated vs actual time
- Historical completion patterns
3. Visual Enhancements
📋 Task #45: Implement User Authentication
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Status: 🟡 in-progress (2 hours)
Priority: 🔴 High | Complexity: 73/100
Dependencies: ✅ #41, ✅ #42, ⏳ #43 (blocked)
Blocks: #46, #47, #52
Progress: ████████░░ 80% complete
Recent Activity:
- 2h ago: Status changed to in-progress
- 4h ago: Dependency #42 completed
- Yesterday: Task expanded with 3 subtasks
4. Intelligent Insights
Based on task analysis:
- Risk Assessment: Complexity vs time remaining
- Bottleneck Analysis: Is this blocking critical work?
- Recommendation: Suggested approach or concerns
- Similar Tasks: How others completed similar work
5. Action Suggestions
Context-aware next steps:
- If blocked → Show how to unblock
- If complex → Suggest expansion
- If in-progress → Show completion checklist
- If done → Show dependent tasks ready to start
6. Multi-Task View
When showing multiple tasks:
- Common dependencies
- Optimal completion order
- Parallel work opportunities
- Combined complexity analysis
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.
- 2d ago First seen · 85 lines · 0 tokens per session scan A 4b4b3313d86e
show-task is a command published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 505 tokens. A static security scan graded it A with 0 findings. It is 97% identical to show-task, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.