feasibility-spike

feasibility-spike is a skill for Claude Code from stanislavnianko/product-discovery-claude-skills. It costs 71 tokens per session (1,128 once invoked), scanned A, original, MIT.

A short, disposable technical experiment used during early product discovery. It tests the riskiest assumptions before the team commits to building the full solution.

In plain words
What is it for?
Use it to test one to three feasibility assumptions, such as whether a proposed approach can work. It reads discovery and risk documents, asks for missing context when needed, and records whether engineering support is available.
Why use it?
It helps reveal major technical problems cheaply and early. The output is deliberately temporary rather than production software.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the discovery-phase plugin — 25 skills shipped together

Good fit Use it to test one to three feasibility assumptions, such as whether a proposed approach can work. It reads discovery and risk documents, asks for missing context when needed, and records whether engineering support is available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike
Install

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.

Any agent
npx skills add stanislavnianko/product-discovery-claude-skills --skill feasibility-spike
Clone the repo
git clone --depth 1 https://github.com/stanislavnianko/product-discovery-claude-skills

Made for: Claude Code.

Or install discovery-phase, the plugin that ships this one along with the rest of its 25 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for feasibility-spike

README.md
[![agentmods](https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike/github.svg)](https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike)
Your own site
<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for feasibility-spike

Your own site · 80×15
<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/feasibility-spike.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01128
Opus 5 $0.00036 $0.00564
Sonnet 5 $0.00014 $0.00226
Haiku 4.5 $0.00007 $0.00113

Measured 12d ago against content hash 6ce6e651f78e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

feasibility-spike 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 12d 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.

plugins/discovery-phase/skills/feasibility-spike/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feasibility Spike

Part of the discovery-phase skill pack · validation group · reads discovery-context.md (run profile-builder first if missing).

Kill the biggest technical risks cheaply. Throwaway by contract.

Step 1 — Read context

Read discovery-context.md (section 3. Engagement → Runner role) and risk-assumption-map.md (anchors the spike to a specific assumption).

If discovery-context.md is missing, ask the BA inline: "who's running the spike — solo BA / BA + engineer / engineering lead?" — tag the output [ASSUMED ENGINEERING]. If risk-assumption-map.md is missing, ask: "name 1–3 feasibility assumptions to test in one sentence each" or proceed as open exploration tagged [EXPLORATION-NOT-SPIKE]. Never block; recommend profile-builder / risk-assumption-mapping for high-stakes work.

Engineering capacity reality-check (warn + confirm, do not halt): if runner is solo BA with no engineering support, warn that the spike will produce a spike-shaped artifact with weak engineering signal. Offer: loop in an engineer, defer the spike to delivery, skip and accept the risk in the proposal, or proceed solo with a ⚠ NO-ENGINEER-OVERRIDE banner at the top of tech-spike-report.md and findings tagged [SPECULATIVE].

Step 2 — State spike goal

One sentence. Tie to a specific assumption from risk-map.

Example: "Prove we can extract structured events from free-text emails with ≥80% precision using a single Claude API call."

Step 3 — Time box

Tier When
Short — 4 hours Ruling out a "is this even possible?" question
Standard — 1-2 days Validating a specific approach against representative inputs
Escalated — up to 1 week Genuinely unknown territory; requires explicit BA + engineering lead sign-off
>1 week This is no longer a spike. Re-frame as prototype-plan.

Stop at the time box. Overrunning spikes are how discovery bleeds into delivery.

Step 4 — Narrowest test

  • Use production-representative inputs, not cherry-picked
  • Throwaway branch / repo named spike/<topic> — never merge to main
  • Prefer manual scripting over frameworks (frameworks hide what you're testing)
  • Logging is essential; UI is irrelevant

Read the full file on GitHub · 94 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 94 lines · 71 tokens per session scan A 6ce6e651f78e

Subscribe to this mod's changes

feasibility-spike is a skill published in the GitHub repository stanislavnianko/product-discovery-claude-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,128 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

jtbd-extractor

Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.

varunk130/ai-customer-discovery-skills · 50 tokens

assumption-mapper

Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before…

varunk130/ai-customer-discovery-skills · 68 tokens

competitive-analyzer

Structured competitive teardown for product discovery - surface the 4-6 dimensions buyers actually weigh, score every competitor on each, and identify exploitable gaps. Use when: competitive analysis, competitor teardown, market positioning, where do we win, where do we lose, competitive gap analysis, competitor audit.

varunk130/ai-customer-discovery-skills · 63 tokens

feedback-prioritizer

Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what…

varunk130/ai-customer-discovery-skills · 82 tokens

north-star-metric-finder

Identifies a candidate North Star Metric (NSM) for a product - the single metric that captures the value the product delivers to its customers and predicts long-term business growth. Tests candidates against five criteria and surfaces input metrics that move it. Use when: north star metric, NSM, single metric that…

varunk130/ai-customer-discovery-skills · 86 tokens

prd-taskmaster

Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…

anombyte93/prd-taskmaster · 80 tokens