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/vibehat/claude-task-manager/update-single-taskgit clone --depth 1 https://github.com/vibehat/claude-task-managerWhat 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 | $0.00590 |
| Opus 5 | $0.00000 | $0.00295 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
update-single-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 update-single-task — 11 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update a single specific task with new information.
Arguments: $ARGUMENTS
Parse task ID and update details.
Single Task Update
Precisely update one task with AI assistance to maintain consistency.
Argument Parsing
Natural language updates:
- "5: add caching requirement"
- "update 5 to include error handling"
- "task 5 needs rate limiting"
- "5 change priority to high"
Execution
task-master update-task --id=<id> --prompt="<context>"
Update Types
1. Content Updates
- Enhance description
- Add requirements
- Clarify details
- Update acceptance criteria
2. Metadata Updates
- Change priority
- Adjust time estimates
- Update complexity
- Modify dependencies
3. Strategic Updates
- Revise approach
- Change test strategy
- Update implementation notes
- Adjust subtask needs
AI-Powered Updates
The AI:
-
Understands Context
- Reads current task state
- Identifies update intent
- Maintains consistency
- Preserves important info
-
Applies Changes
- Updates relevant fields
- Keeps style consistent
- Adds without removing
- Enhances clarity
-
Validates Results
- Checks coherence
- Verifies completeness
- Maintains relationships
- Suggests related updates
Example Updates
/project:tm/update/single 5: add rate limiting
→ Updating Task #5: "Implement API endpoints"
Current: Basic CRUD endpoints
Adding: Rate limiting requirements
Updated sections:
✓ Description: Added rate limiting mention
✓ Details: Added specific limits (100/min)
✓ Test Strategy: Added rate limit tests
✓ Complexity: Increased from 5 to 6
✓ Time Estimate: Increased by 2 hours
Suggestion: Also update task #6 (API Gateway) for consistency?
Smart Features
-
Incremental Updates
- Adds without overwriting
- Preserves work history
- Tracks what changed
- Shows diff view
-
Consistency Checks
- Related task alignment
- Subtask compatibility
- Dependency validity
- Timeline impact
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 · 130 lines · 0 tokens per session scan A d689d15b3236
update-single-task is a command published in the GitHub repository vibehat/claude-task-manager (21 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. A static security scan graded it A with 0 findings. It is 100% identical to update-single-task, differing in 11 lines, and is treated as a copy.
Other commands, from other repositories
deploy_to_docker
Build Docker image and start/redeploy the MCP Task Orchestrator container, reusing the last-used config by default.
check_schema_version
Check the Flyway schema version of the SQLite database on a Docker volume.
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.