run-spike

run-spike is a skill for Claude Code, Codex from leifericf/agentic-sdk. It costs 0 tokens per session (1,670 once invoked), scanned A, original, MIT.

A short, focused investigation into a major unknown that could affect a software plan. It uses a temporary test harness to gather evidence and ends with a go, no-go, or mitigation decision.

In plain words
What is it for?
Use it to test a risky technical seam under expected and higher loads, answer a specific factual question, and decide whether to proceed, change the plan, or reduce the risk.
Why use it?
It prevents teams from planning around guesses about difficult areas such as native-code boundaries, performance limits, or concurrency.

Skill for Claude CodeCodex

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 skills/leifericf/agentic-sdk/run-spike
Any agent
npx skills add leifericf/agentic-sdk --skill run-spike
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

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 run-spike

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/run-spike.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/run-spike)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/run-spike"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/run-spike.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00000 $0.01670
Opus 5 $0.00000 $0.00835
Sonnet 5 $0.00000 $0.00334
Haiku 4.5 $0.00000 $0.00167

Measured 4d ago against content hash 9dc777d8be6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-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 4d 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.

skills/run-spike/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

run-spike

A spike buys knowledge, not a feature. Run one when a load-bearing unknown sits in front of real work and you cannot plan past it honestly. Front-load the biggest unknowns, the ones at the seams: the native edge (a C ABI, NIF, or foreign-function boundary that may leak or crash under churn), a real-time budget a renderer or audio path must hit, a concurrency model the single-threaded path hides.

A spike learns; a feature ships. When the answer is known and the work is to build the planned thing, that is implement-change. When the work is to break existing code, that is adversarial-test. A spike has no user; its deliverable is a decision plus, sometimes, a harness worth keeping.

Procedure

The discipline, in order. Do not skip steps.

1. Name the unknown and the question

Write down, in one or two sentences each:

  • The load-bearing unknown. The thing that, if it goes the wrong way, changes the plan.
  • The question the spike must answer, phrased so the answer is a fact, not an opinion. "Does a hundred thousand native-handle create and free cycles return allocation to zero?" not "Is the native edge good enough?" A fuzzy question produces a fuzzy decision.
  • The decision the answer unblocks: which planned work waits on this, and what the go, no-go, and mitigate branches each mean for it.

State all three to the maintainer before building anything. The spike is scoped wrong if you cannot.

2. Time-box it

Set a budget up front: hours, or a fixed number of harness iterations. A spike runs until it answers the question or the box closes, whichever comes first. A box that closes with no clear answer is itself a finding: the seam is harder to characterize than expected, and that goes in the write-up. Do not let a spike slide into building the feature because the harness started to look real.

3. Build a standalone, throwaway harness

The harness is scaffolding, not product. Build it to be discarded (step 7 decides if any earns a place). Keep it isolated: its own namespace, module, or file under a spike path, no edits to the modules it probes, scratch state under a tmp dir.

Read the full file on GitHub · 157 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. 4d ago First seen · 157 lines · 0 tokens per session scan A 9dc777d8be6e

Subscribe to this mod's changes

run-spike is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,670 tokens. 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens