feasibility — Claude Code command: project assessment and setup
feasibility is a command that assesses whether a project can meet its constraints and recommends whether to proceed, revise terms, or stop.
MIT ★ 1,988 updated 2026-04-01
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resourcesWhat feasibility does
The command first checks the project context and asks about gaps in constraints, complexity, dependencies, or risk tolerance. Once you answer, it offers a chance to clarify further before starting the assessment.
Its report covers technical, resource, and external dependency feasibility, with blockers, mitigation options, and an overall verdict. It also suggests a starting point, critical path, and fallback scope. The completed research is saved as a dated Markdown file under artifacts/research/. Since it uses AskUserQuestion, assessment follows an interactive intake rather than running straight from the initial prompt.
What it helps with
- check whether a project fits its technical and resource constraints
- find external dependency risks before implementation
- identify blockers and ways to reduce project risk
- save a feasibility report for later reference
Example prompts for the agent
- Assess whether we can add PDF report exports under these constraints.
- Check the feasibility of this migration and save the assessment.
- Review this idea’s external dependencies and suggest ways to reduce risk.
How to install feasibility
1Plugin marketplace
/plugin marketplace add glittercowboy/taches-cc-resources/plugin install taches-cc-resources@taches-cc-resources2Manually: put the files in place
.claude/commands/feasibility.mdCall it with /feasibility. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/feasibility.mdCall it with /prompts:feasibility. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/feasibility.prompt.mdManually: put the files in place
.gemini/commands/feasibility.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about feasibility
How do I install feasibility in Claude Code?
Add the marketplace with /plugin marketplace add glittercowboy/taches-cc-resources, then install the command with /plugin install taches-cc-resources@taches-cc-resources.
What does feasibility do?
It assesses a project’s technical, resource, and external dependency constraints, then gives a verdict with blockers and mitigation options. The report is saved under artifacts/research/.
What does feasibility ask before starting its assessment?
It asks about context gaps such as constraints, project complexity, external dependencies, and risk tolerance. Questions already answered in your request are skipped.
Source text
feasibility.md · MIT
--- description: Reality check - can we actually do this with our constraints? argument-hint: [idea/project or leave blank for current context] --- <objective> Assess feasibility of $ARGUMENTS (or the current topic if no arguments provided). Honest reality check: can we actually do this given technical, resource, and external constraints? </objective> <intake_gate> <context_analysis> First, analyze $ARGUMENTS to extract what's already provided: - What's being assessed - Known constraints (budget, API limits, external dependencies) - Technical requirements - Risk tolerance Only ask about genuine gaps - don't re-ask what's already stated. </context_analysis> <initial_questions> Use AskUserQuestion to ask 2-4 questions based on actual gaps: **If constraints unclear:** - "Any hard constraints?" with options: Budget limits, API/service restrictions, Must use specific tech, No major constraints, Other **If complexity unclear:** - "How complex is this?" with options: Small (few components), Medium (multiple systems), Large (significant architecture), Not sure, Other **If dependencies unclear:** - "External dependencies?" with options: Third-party APIs, External services, Other projects, None significant, Other **If risk tolerance unclear:** - "How certain do you need to be?" with options: High confidence required, Moderate risk OK, Willing to experiment, Other Skip questions where $ARGUMENTS already provides the answer. </initial_questions> <decision_gate> After receiving answers, use AskUserQuestion: Question: "Ready to assess feasibility, or would you like me to ask more questions?" Options: 1. **Start assessment** - I have enough context 2. **Ask more questions** - There are details to clarify 3. **Let me add context** - I want to provide additional information If "Ask more questions" → generate 2-3 contextual follow-ups, then present decision gate again If "Let me add context" → receive input, then present decision gate again If "Start assessment" → proceed to research </decision_gate> </intake_gate> <process> After intake complete: 1. Define what we're assessing 2. Evaluate technical feasibility 3. Evaluate resource feasibility 4. Evaluate external dependency feasibility 5. Identify blockers and de-risking strategies 6. Make go/no-go recommendation </process> <output_format> ## Feasibility Assessment: [Project/Idea] ### Strategic Summary [2-3 sentences: verdict, main concern, key condition for success] ### What we're assessing [Clear description of the proposed project/feature] ### Technical Feasibility **Can we build it?** - Known approaches: [Yes/Partial/No] - [details] - Technology maturity: [Proven/Emerging/Experimental] - Technical risks: [List with severity] - **Technical verdict:** Feasible / Risky / Not feasible ### Resource Feasibility **Do we have what we need?** - Skills: [Have/Need to learn] - Budget: [Sufficient/Tight/Insufficient] - Tools/infrastructure: [Have/Need to acquire] - **Resource verdict:** Feasible / Risky / Not feasible ### External Dependency Feasibility **Are external factors reliable?** - APIs/services: [Available/Reliable/Rate limits] - Third-party integrations: [Stable/Risky] - External data: [Accessible/Restricted] - **External verdict:** Feasible / Risky / Not feasible ### Blockers | Blocker | Severity | Mitigation | |---------|----------|------------| | [Blocker] | High/Med/Low | [How to address] | ### De-risking Options - [Option]: [How it reduces risk, what it costs] - [Option]: [How it reduces risk, what it costs] ### Overall Verdict **[Go / Go with conditions / No-go]** [Reasoning and key conditions] ### Implementation Context <claude_context> <if_go> - approach: [recommended technical approach] - start_with: [first thing to build/validate] - critical_path: [what must work for this to succeed] </if_go> <risks> - technical: [main technical risks] - external: [main dependency risks] - mitigation: [how to address each] </risks> <alternatives> - if_blocked: [fallback approaches if primary fails] - simpler_version: [reduced scope that's definitely feasible] </alternatives> </claude_context> **Next Action:** Address blockers, reduce scope, prototype critical path, or proceed to /plan/project ### Sources - [Source name]: [URL] - [date accessed] - [Source name]: [URL] - [date accessed] </output_format> <artifact_output> Save the research to a file: 1. Create directory structure if it doesn't exist: - `[current-working-directory]/artifacts/research/` 2. Generate filename from topic: - Get current date in YYYY-MM-DD format - Slugify the topic (lowercase, hyphens for spaces) - Format: `YYYY-MM-DD-[topic]-feasibility.md` - Example: `2025-01-15-native-app-migration-feasibility.md` 3. Write the complete research to the file 4. Report to user: "Saved to `artifacts/research/[filename]`" </artifact_output> <success_criteria> - Assessment is honest (not optimistic or pessimistic) - All dimensions evaluated (technical, resource, external) - Blockers are specific and addressable - De-risking options are actionable - Verdict is clear with reasoning - Implementation context gives Claude clear path forward - Enables informed go/no-go decision - Output saved to artifacts/research/ directory </success_criteria>
© Lex Christopherson · MIT · glittercowboy/taches-cc-resources