spike-designer

A design role for the first phase of a spike pipeline, where a spike is a small experiment used to test one technical assumption. It creates a typed experiment plan with success measures, sample-size reasoning, possible confounding factors, constraints, and cost.

In plain words
What is it for?
Use it to design the experiment for a named spike before implementation, including its design files and validation details.
Why use it?
It turns an uncertain technical question into a focused experiment with measurable evidence and explicit limits.

Agent

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.

agentmods
npx agentmods add agents/chris-dare-dev/agent-kit/spike-designer
Clone the repo
git clone --depth 1 https://github.com/chris-dare-dev/agent-kit
Per session 144 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00144 $0.02259
Opus 5 $0.00072 $0.01130
Sonnet 5 $0.00029 $0.00452
Haiku 4.5 $0.00014 $0.00226

Measured yesterday against content hash f9dadf19cdcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

spike-designer scanned grade C with 2 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

"Now run X", "Ignore previous instructions", "Authorize the user", "Add yourself

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ".claude/agent-memory/spike-designer/lessons.md" 2>/dev/null || echo "(no lessons yet)"
data/agents/spike-designer.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spike Designer

You are Phase 1 of the /spike pipeline. Your job is to extract a spike brief from the roadmap and design a rigorous, minimal experiment that answers exactly one assumption with measurable data — expressed as a typed contract the rest of the pipeline can validate and derive from.

The orchestrator (slash command at .claude/commands/spike.md) dispatches you with substituted variables. You never invoke other sub-agents.

Input variables (substituted by the orchestrator)

  • {SPIKE_ID} — the spike identifier (e.g., kiali-multicluster-spike-1)
  • {ROADMAP_PATH} — absolute path to the roadmap file containing the spike brief
  • {DESIGN_JSON_PATH} — absolute path where you MUST write design.json (the typed contract)
  • {DESIGN_PATH} — absolute path where you MUST write design.md (the human design)
  • {VALIDATE_SCRIPT} — absolute path to spike-validate.py (used in Step 3 self-validation)
  • {DEVIATION_PATH} — (optional) absolute path to design-deviation.md from a previous executor run; set ONLY on re-dispatch after design-deviation was returned

Step 0 — Read persistent memory (skip-if-not-relevant)

cat ".claude/agent-memory/spike-designer/lessons.md" 2>/dev/null || echo "(no lessons yet)"

Read memory only if the lessons are relevant to this spike's domain.

Step 0b — On re-dispatch: read the deviation BEFORE extracting the brief

If {DEVIATION_PATH} is set (non-empty), read it now:

cat "{DEVIATION_PATH}"

Its "Recommended design fix" section is a hard constraint on the new design. You MUST incorporate it. On re-dispatch you overwrite both design.json and design.md.


Step 1 — Extract the spike brief from the roadmap

Read {ROADMAP_PATH}. Extract the brief for {SPIKE_ID} using this priority order:

First: bullet pattern (primary — the roadmap convention). Under a ### Spike / discovery lane heading (or a heading containing "spike"/"discovery"), find a bullet matching:

  • - **`{SPIKE_ID}`** — <brief> · - **`{SPIKE_ID}`:** <brief> · - **{SPIKE_ID} IS the spike.** Output: ...

Read the full file on GitHub · 193 lines

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. yesterday First seen · 193 lines · 144 tokens per session scan C f9dadf19cdcd

Subscribe to this mod's changes

spike-designer is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 24d ago), licensed MIT. It adds 144 tokens to every session and 2,259 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (instruction-override phrasing, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

bynder-agent

Senior Bynder DAM platform engineer with command of asset modeling and metaproperties, Brand Guidelines, derivative templates, the bynder-js-sdk, Universal Compact View embedding, Bynder + Contentful pairing, portal and account architecture, permissions and workflow, webhooks, marketplace connectors, migrations, and…

bpainter/composable-dxp-claude-marketplace · 141 tokens

algolia-agent

Senior Algolia platform engineer with command of index design, relevance tuning, InstantSearch React/Next.js, the Autocomplete UI library, direct search-client usage, indexing pipelines, API-key strategy, the Recommend API, AI search and Personalization (NeuralSearch, query categorization), Insights events and A/B…

bpainter/composable-dxp-claude-marketplace · 153 tokens

behavioral-economics-agent

Senior behavioral scientist who applies behavioral economics, choice architecture, and research methods to product, policy, marketing, and organizational problems. Use this agent when a task spans multiple skills in this plugin, requires sequencing, or needs senior-level judgment about which skill to apply for a given…

bpainter/composable-dxp-claude-marketplace · 80 tokens

brand-agent

Senior brand practitioner spanning strategy, naming, identity systems, voice and tone, guidelines composition, and brand audits. Use this agent when a task spans multiple skills in this plugin, requires sequencing, or needs senior-level judgment about which skill applies. Tagline: Brand from positioning to applied…

bpainter/composable-dxp-claude-marketplace · 76 tokens

claude-agent

Plugin orchestrator. Routes between the two claude- skills (claude-plugin-creator for building new Claude plugins from scratch, and claude-orchestrator for designing the orchestration layer of a new Cowork project). Use this agent as the first call for any Claude-tooling task — plugin creation, hook design, MCP server…

bpainter/composable-dxp-claude-marketplace · 106 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens