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/sergiovision/devserver/devtasknpx skills add sergiovision/DevServer --skill devtaskgit clone --depth 1 https://github.com/sergiovision/DevServerWhat 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 | $0.00704 |
| Opus 5 | $0.00015 | $0.00352 |
| Sonnet 5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
devtask 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 yesterday.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTask - Generate Task JSON
You receive a free-form task description in $ARGUMENTS. Return only a single JSON object (no markdown fences, no explanation) that can be POSTed to POST /api/tasks.
Do NOT explore or read the target repo. The executing agent has full repo access — your job is to write a clear, compact spec from the user's description alone. Save tokens.
Output Schema
{
"task_key": "<string>",
"title": "<string>",
"description": "<string>",
"acceptance": "<string|null>",
"priority": <1|2|3|4>,
"labels": ["<string>", ...],
"mode": "autonomous",
"claude_mode": "api",
"claude_model": "<string|null>",
"max_turns": <number|null>,
"skip_verify": false
}
repo_id is omitted — the caller supplies it.
Field Rules
- task_key: UPPERCASE hyphenated slug,
AREA-SHORT-SLUGformat, max 64 chars. - title: Imperative, under 100 chars.
- description: Concise actionable spec. State what to do, not how to find it. The executing agent will explore the repo itself — don't guess file paths or implementation details you don't know. Include edge cases only if obvious from the request.
- acceptance: Bullet list of testable criteria, or
nullif trivial. Keep short — 2-5 bullets max. - priority: 1=critical/prod-down, 2=high/blocking, 3=medium (default), 4=low/cosmetic.
- labels: 1-3 lowercase kebab-case. Common:
feature,bug,refactor,ui,api,database,docs,security,performance,devops. - claude_model:
null(repo default) for most tasks."claude-sonnet-4-20250514"for simple/well-defined."claude-opus-4-20250514"for complex/multi-file/security. - max_turns: Simple fix: 10-20. Small feature: 20-40. Medium: 40-60. Large: 60-100. Open-ended:
null. - mode: Always
"autonomous"unless explicitly interactive. - claude_mode: Always
"api"unless user says Max. - skip_verify: Always
falseunless user says skip.
Rules
- Output ONLY valid JSON. No fences, no explanation.
- Do NOT include system fields:
repo_id,id,status,created_by,created_at,updated_at,depends_on,bullmq_job_id. - Never invent requirements not implied by the description.
- If description is too vague for acceptance criteria, set
acceptancetonull.
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.
- yesterday First seen · 55 lines · 31 tokens per session scan A 5e8ffa0ecee3
devtask is a skill published in the GitHub repository sergiovision/DevServer (1 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 704 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
wiki-write
Add or update wiki content — autonomous ingest from URL, file, or text; autonomous update of existing pages. Auto-creates .wiki/ on first use. Use when: 'save to wiki', 'remember this', 'note this', 'store this', 'add to knowledge base', 'save findings', 'save research', 'save idea', 'write to wiki', 'ingest', 'add…
wiki-serve
Start the wiki web server — browsable Wikipedia-style UI with live research, split-pane editor, AI assist, and themes. Manual trigger only: /wiki-serve, 'start wiki server', 'browse the wiki'.
wiki-maintain
Wiki maintenance — lint broken links, merge near-duplicates, upgrade confidence, flag stale pages via freshness tiers, gap analysis, concept synthesis. Use on: 'wiki maintenance', 'wiki cleanup', 'fix wiki', 'wiki health', 'check wiki', 'consolidate wiki'.
wiki-read
Search and query the wiki — get cited answers, with automatic research when knowledge is missing. Three depth modes. Use when: 'check wiki', 'what do we know about', 'look up', 'find in wiki', 'search wiki', 'search for', 'find information about', 'do we have notes on', 'wiki context', 'existing knowledge'…
wiki-view
Wiki dashboard — browse pages, view stats, knowledge graph, export. Use on: 'wiki dashboard', 'wiki stats', 'show wiki', 'wiki pages', 'list wiki', 'wiki graph', 'export wiki', 'wiki overview'.
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.