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 skills/mandrianova/jb-task-manager-extension/task-executenpx skills add mandrianova/jb-task-manager-extension --skill task-executegit clone --depth 1 https://github.com/mandrianova/jb-task-manager-extensionWhat 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 | $0.00035 | $0.02040 |
| Opus 5 | $0.00017 | $0.01020 |
| Sonnet 5 | $0.00007 | $0.00408 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
task-execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Execute
You are executing tasks from the project's task management system.
Resolve TASKS_DIR before running commands:
- If
TASK_MANAGER_TASKS_DIRis set, use that. - Else if
.claude/tasksexists, use.claude/tasksfor backward compatibility. - Else if
.agents/tasksexists, use.agents/tasks. - Else if
.kiro/tasksexists, use.kiro/tasks. - Else if
.idea/agents-tasksexists, use.idea/agents-tasks. - Else if
TASK_MANAGER_AGENT=codexor you are running in Codex, use.agents/tasks; ifTASK_MANAGER_AGENT=kiro-clior you are running in Kiro, use.kiro/tasks; otherwise use.claude/tasks.
CLI helper
IMPORTANT: Always use a relative path for task-cli.sh — never an absolute path. This ensures permission rules match correctly.
TASKS_DIR="${TASK_MANAGER_TASKS_DIR:-$(case "${TASK_MANAGER_AGENT:-}" in codex) echo .agents/tasks ;; kiro|kiro-cli) echo .kiro/tasks ;; *) echo .claude/tasks ;; esac)}"
# List active tasks (includes tracker config at the top)
bash "$TASKS_DIR/task-cli.sh" list
# List tasks in a specific group (active only by default)
bash "$TASKS_DIR/task-cli.sh" list --group <groupId>
# List ALL tasks including completed/cancelled
bash "$TASKS_DIR/task-cli.sh" list --all
# Filter by specific status
bash "$TASKS_DIR/task-cli.sh" list --status in_progress
# Get full JSON details of a task or group
bash "$TASKS_DIR/task-cli.sh" get <id>
# Update task status
bash "$TASKS_DIR/task-cli.sh" status <taskId> <status>
# Attach commit hash to a task
bash "$TASKS_DIR/task-cli.sh" commit <taskId> <commitHash>
# Create a new subtask
bash "$TASKS_DIR/task-cli.sh" add-task <groupId> "<name>" "<description>"
Note: list outputs tracker config automatically — no need to call config separately.
If task-cli.sh is not found at $TASKS_DIR/task-cli.sh, check scripts/task-cli.sh and copy it.
Permissions check
Before starting in Claude Code, check if .claude/settings.local.json exists. If it doesn't, suggest the user create it with the recommended permissions:
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 · 190 lines · 35 tokens per session scan A a89461010ebb
task-execute is a skill published in the GitHub repository mandrianova/jb-task-manager-extension (4 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 2,040 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…