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/mp-web3/claude-starter-kit/tasksnpx skills add mp-web3/claude-starter-kit --skill tasksgit clone --depth 1 https://github.com/mp-web3/claude-starter-kitWhat 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 | $0.00031 | $0.01309 |
| Opus 5 | $0.00015 | $0.00655 |
| Sonnet 5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
tasks 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tasks — Task Management (SQLite-backed)
First: Read LEARNINGS.md (in this skill's directory) before proceeding.
Primary store: tasks.db (in workspace root). Markdown export at state/backlog.md (read-only, regenerated on changes).
Arguments: $ARGUMENTS
Routing
| Input | Action |
|---|---|
(empty) or status |
Show Status |
add <description> |
Add Task |
review |
Review & Reprioritize |
done T### |
Complete Task |
metrics |
Show Metrics |
Show Status
# Active tasks sorted by priority
sqlite3 ~/claude-assistant/tasks.db -header -column \
"SELECT id, name, priority, status, effort, problems FROM tasks WHERE status != 'done' ORDER BY CASE priority WHEN 'P1' THEN 1 WHEN 'P2' THEN 2 WHEN 'P3' THEN 3 ELSE 4 END, id"
# Blocked tasks
sqlite3 ~/claude-assistant/tasks.db -header -column \
"SELECT id, name, blocked_by, blocked_reason FROM tasks WHERE blocked_by IS NOT NULL AND status != 'done'"
# Counts
sqlite3 ~/claude-assistant/tasks.db \
"SELECT (SELECT COUNT(*) FROM tasks WHERE status NOT IN ('done')) AS active, (SELECT COUNT(*) FROM tasks WHERE status='done') AS completed, (SELECT COUNT(*) FROM tasks WHERE blocked_by IS NOT NULL AND status != 'done') AS blocked"
Flag:
- Any P1 task not
in_progress-- prompt to start it - Any task
in_progressfor 7+ days (check updated_at) -- suggest reviewing
Add Task
- Parse
<description>from arguments - Get next ID:
sqlite3 ~/claude-assistant/tasks.db "SELECT value FROM config WHERE key='next_id'" - Read
knowledge/problems/00-overview.mdto know the user's problems - Ask: which problems (by number) does this relate to? Effort (S/M/L)? Which subgoal?
- Evaluate priority:
- Problems >= 3 -- strong P1 candidate
- Problems >= 2 + urgency -- P2
- Problems == 1 or no urgency -- P3
- Problems == 0 -- flag: "Is this drift?"
- On approval, insert via sqlite3:
sqlite3 ~/claude-assistant/tasks.db "INSERT INTO tasks (id, name, priority, problems, effort, status, subgoal, created_at, updated_at) VALUES ('T###', 'Name', 'P2', '1,4', 'M', 'pending', 'S1', '$(date +%Y-%m-%d)', '$(date -u +%Y-%m-%dT%H:%M:%SZ)')"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 129 lines · 31 tokens per session scan A 0f9bdbd92a9e
tasks is a skill published in the GitHub repository mp-web3/claude-starter-kit (106 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,309 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 2026-08-30.
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…