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/snarktank/code-editing-agent/show-taskgit clone --depth 1 https://github.com/snarktank/code-editing-agentWhat 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 | $0.00495 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
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
100% identical to show-task — 0 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 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 · 82 lines · 0 tokens per session scan A 0cc3d53377f1
show-task is a command published in the GitHub repository snarktank/code-editing-agent (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 tokens. A static security scan graded it A with 0 findings. It is 100% identical to show-task, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.