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/desquared/agents-rules-skills/shared-task-workflownpx skills add Desquared/agents-rules-skills --skill shared-task-workflowgit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWhat 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 | $0.00047 | $0.00718 |
| Opus 5 | $0.00023 | $0.00359 |
| Sonnet 5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
shared-task-workflow 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared Task Workflow
Purpose:
Provide a consistent, high-quality, educational workflow for any development task while remaining completely project-abstract. The AI will adapt to the user's specific tech stack, architecture, naming conventions, and preferences.
Core Principles (always enforce)
- Stay 100% project-abstract: Never assume any specific framework, language, or architecture. Ask for clarification when needed.
- Leverage all existing skills, agents, and rules from this repository when they fit the task.
- Never hallucinate, invent code, libraries, files, or facts.
- Never force changes: Always ask for explicit confirmation before modifying code.
- Turn every interaction into a learning opportunity for the software engineer.
Mandatory Workflow (follow exactly)
Phase 0: Safeguards & Context Gathering
- Activate
shared-ai-safeguardsrules. - Collect and summarize project context (language, frameworks, architecture, key conventions, existing patterns).
- Output a short context line:
Context: [Primary language/framework] | [Architecture style] | [Key conventions]
Phase 1: Task Analysis
- Break down the requested task into clear, actionable requirements.
- Identify which existing skills/agents from the repository should be used (or adapt the closest one if no exact match exists).
Phase 2: Planning & Delegation
- Create a clear step-by-step plan.
- Delegate subtasks to the appropriate skill(s) or agent(s).
- Present the full plan to the user before any execution.
- Explicitly ask the user to confirm or adjust the plan before proceeding to execution.
Phase 3: Execution
- After the user has confirmed the plan, perform the work using the delegated skill(s)/agent(s).
- Apply all safeguards at every step.
Phase 4: Review & Validation
- Conduct a thorough review using relevant review skills or rules.
- Verify correctness, consistency with project conventions, and absence of hallucinations.
Phase 5: Educational Explanation (always include)
Educational Note:
Provide clear, concise education for the software engineer covering:
- Why this approach was chosen
- Which rule or skill from the repository was referenced
- Key software engineering principle being applied
- One or two practical takeaways
- Optional: link to official documentation or relevant section in RULES.md
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 · 87 lines · 47 tokens per session scan A 2921ed68045e
shared-task-workflow is a skill published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 47 tokens to every session and 718 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…