technical-spike

A limited investigation used to answer one external or version-specific technical question that blocks a correct decision. It checks local project evidence first, then uses authoritative documentation, specifications, source code, release notes, or a small reproduction if needed.

In plain words
What is it for?
Use it to resolve compatibility questions, confirm how a particular version behaves, or compare options needed by the current task. The result records observed facts, conclusions, task impact, and remaining uncertainty.
Why use it?
It prevents design and implementation choices from depending on guesses about a framework, library, tool, runtime, protocol, or platform. A clear stopping point keeps the research focused.

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/yarlson/yarstack/technical-spike
Any agent
npx skills add yarlson/yarstack --skill technical-spike
Clone the repo
git clone --depth 1 https://github.com/yarlson/yarstack

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 305 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 $0.00045 $0.00305
Opus 5 $0.00023 $0.00152
Sonnet 5 $0.00009 $0.00061
Haiku 4.5 $0.00005 $0.00030

Measured 2d ago against content hash 61bc16fbdc8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-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 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.

plugins/yarstack/skills/technical-spike/SKILL.md · 24 lines

What it actually says

Technical Spike

Own extended technical investigation while the calling workflow retains its planning, implementation, or validation decision.

Workflow

  1. State the exact question, applicable versions, decision it blocks, and stopping condition.
  2. Check local manifests, lockfiles, configuration, code, tests, installed versions, and command help first.
  3. When local evidence is insufficient, use the most authoritative relevant primary source: official documentation, specifications, upstream source, release notes, or a bounded reproduction.
  4. Require explicit authority before network access, dependency changes, repository edits, external writes, or experiments with side effects. Keep temporary reproductions outside the repository unless the task authorizes a durable test.
  5. Separate observed facts from inference and record only conclusions that affect the current task.
  6. Translate evidence into concrete design, compatibility, implementation, or verification implications.

Report the question, applicable versions, local and external source references, observed facts, inference, conclusion, task impact, remaining uncertainty, and stopping decision.

Do not research adjacent features, upgrade dependencies, add abstractions to hide uncertainty, or present unresolved behavior as confirmed. Return unresolved uncertainty as a blocker or explicit risk.

Finish when the current task has a supported path forward or further evidence requires new authority or unavailable state.

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. 2d ago First seen · 24 lines · 45 tokens per session scan A 61bc16fbdc8b

Subscribe to this mod's changes

technical-spike is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 305 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.

Related

Other skills, from other repositories

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

release-cli

Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…

851-labs/tokenmaxxing · 73 tokens

ship-mobile-app

Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…

aiopshwang/ship-mobile-app · 103 tokens

verify-regression-tests

Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…

aiopshwang/verify-regression-tests · 75 tokens

repository-bootstrap

Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.

cz1993/vibe-coding-repository-standard · 41 tokens

repository-hygiene

Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.

cz1993/vibe-coding-repository-standard · 52 tokens