crucible-investigation-methodology

crucible-investigation-methodology is a skill for Claude Code from terrylica/cc-skills. It costs 29 tokens per session (2,018 once invoked), scanned A, original, MIT.

A six-part method for testing new research hypotheses, especially when working with numerical market data. It includes converting data into patterns that language models can compare and checking results through several independent tests.

In plain words
What is it for?
Use it to represent market data for model analysis, compare hypotheses, and test promising results against adversarial or out-of-sample checks.
Why use it?
It addresses the risk of mistaking a result seen in historical data for a strategy that will work elsewhere. Multiple checks make weak or accidental findings easier to reject.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the crucible plugin — 5 skills shipped together

Good fit Use it to represent market data for model analysis, compare hypotheses, and test promising results against adversarial or out-of-sample checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrylica/cc-skills/b-investigation-methodology
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 terrylica/cc-skills --skill b-investigation-methodology
Clone the repo
git clone --depth 1 https://github.com/terrylica/cc-skills

Made for: Claude Code.

Or install crucible, the plugin that ships this one along with the rest of its 5 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 crucible-investigation-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/b-investigation-methodology/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/b-investigation-methodology)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/b-investigation-methodology"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/b-investigation-methodology/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 crucible-investigation-methodology

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/b-investigation-methodology"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/b-investigation-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00029 $0.02018
Opus 5 $0.00015 $0.01009
Sonnet 5 $0.00006 $0.00404
Haiku 4.5 $0.00003 $0.00202

Measured 6d ago against content hash 6334de8a9239, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

crucible-investigation-methodology 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 6d 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/crucible/skills/b-investigation-methodology/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigation Methodology — 6 execution patterns

Self-Evolving Skill: If any pattern here fails in practice (wrong results, wasted compute), update the section AND append to references/evolution-log.md. Don't defer.

These 6 patterns executed in service of a-research-foundations. They are the "how" to the foundations' "why". Apply in roughly this order for a new hypothesis.


1. LLM-native data representation — quintile tokens

Before asking an agent to "look at" numerical market data, encode as per-bar token sequences using rolling quintile ranks within a causal window.

Canonical schema:

idx  dir  body_q  range_q  dur_q  uwick_q  lwick_q  loc  sess  fwd+H...

Each quintile is 1..5 in a causal 200-bar rolling window (see Skill A §1). Agents can spot motifs like +1:5:1|+1:5:1|+1:5:1 (three consecutive fast big-up bars) that are invisible in float-space.

Context-budget rule: 60 KB tokenized stats-table fits in agent context; 67 MB raw bars don't.

Full reference: findings/methodology/01-llm-native-data-representation.md.


2. Serial adversarial gates (A/B/C/D/E protocol)

Before trusting any in-sample positive, survive 4-5 independent gates in series.

Gate Question Catches
A — Directional breakdown Is edge from long/short/both? Diffusive-looking edges that are actually directional
B — Mirror symmetry Does the inverse trigger show mirror edge? Sample-window drift inflating one side
C — OOS time-split (80/20 chronological) Does finding survive on held-out later data? In-sample overfit
D — Cross-asset replay Does it replicate on other symbols? Asset-specific overfit
E — Full-history per-year Is it positive in ≥60% of years? Single-year-luck

Read the full file on GitHub · 190 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. 6d ago Changed 6334de8a9239
  2. 11d ago First seen · 190 lines · 29 tokens per session scan A c8190bc05a00

Subscribe to this mod's changes

crucible-investigation-methodology is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,018 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

finance

Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.

travisjneuman/.claude · 48 tokens

financial-scenario-planner

Stress-test financial plans across scenarios (bull/bear/base), sensitivity tables, and Monte Carlo-style analysis. Use when evaluating financial assumptions, modeling risk scenarios, or building scenario-based financial plans.

travisjneuman/.claude · 44 tokens

investment-memo-generator

Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.

travisjneuman/.claude · 37 tokens

debug-systematic

Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.

travisjneuman/.claude · 33 tokens

embedded-iot

Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.

travisjneuman/.claude · 80 tokens

generic-code-reviewer

Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.

travisjneuman/.claude · 70 tokens