Discovery Loop

Discovery Loop is a skill for Claude Code from ralfyishere/rules-with-receipts. It costs 142 tokens per session (1,437 once invoked), scanned A, original, MIT.

An investigation method for repeatedly creating and testing new explanations or ideas against live evidence. It keeps a record of how strongly each belief is supported and actively looks for evidence that could disprove it.

In plain words
What is it for?
For ongoing investigations into market opportunities, recurring incidents, performance slowdowns, growth experiments, and research questions.
Why use it?
It prevents a closed conclusion or a short run of confirming results from ending the investigation too early. A failed test becomes a reason to explore another possibility, not proof that none can work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit For ongoing investigations into market opportunities, recurring incidents, performance slowdowns, growth experiments, and research questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ralfyishere/rules-with-receipts/discovery-loop
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 ralfyishere/rules-with-receipts --skill discovery-loop
Clone the repo
git clone --depth 1 https://github.com/ralfyishere/rules-with-receipts

Made for: Claude Code.

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 Discovery Loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/discovery-loop.svg)](https://agentmods.dev/skills/ralfyishere/rules-with-receipts/discovery-loop)
Your own site
<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/discovery-loop"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/discovery-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,437 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 $0.00142 $0.01437
Opus 5 $0.00071 $0.00718
Sonnet 5 $0.00028 $0.00287
Haiku 4.5 $0.00014 $0.00144

Measured 7d ago against content hash c4b18af9d87b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Discovery Loop 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 7d 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.

.claude/skills/discovery-loop/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery Loop

Purpose

Verification kills bad ideas; nothing in a kill-oriented process creates new ones. A finished investigation with an honest verdict ("no edge found", "not reproducible", "root cause is X") quietly becomes a wall: future sessions treat the kill-list as the space. The two documented failures this skill exists for: (1) a universal negative read off a finite list — "we tested 9 strategies, all dead" became "no edge exists," until an outsider's success disproved it in one evening; (2) belief moving on vibes — credence climbing through a streak of confirmations with no attack, or a "winner" anointed from a short window that a full-history audit later showed was net-negative. The loop makes generation a standing duty and belief an explicit, attackable number.

When to use this skill

  • Standing investigations that survive across sessions: market/edge hunts, recurring incidents, performance regressions, growth experiments, research programs.
  • A verdict/kill-list exists and is about to be cited as the reason not to look.
  • External evidence contradicts your closed conclusion (a competitor does the "impossible" thing) — that is a lead, not an annoyance.
  • You notice every recent hypothesis came from your own head, none from observation.

When NOT to use

  • One-shot tasks with a definite end (a bug fixed and verified; a question answered).
  • Domains where more hypotheses have no value (the decision is made, the system is being decommissioned).
  • As a license to re-litigate a kill WITHOUT new evidence — re-opening requires a new observation, not boredom with the verdict.

The loop (every session the investigation is touched)

  1. Observe before theorizing. Spend the first cycle on what the domain is DOING now — who is succeeding, what changed, what the live data shows — via the cheapest real-observation channel (public fills, logs, dashboards, competitor output). Winners' observed behavior outranks your priors as a hypothesis source.
  2. Generate ≥1 NEW hypothesis, dated, even half-baked. From the observation, not from re-reading old brainstorms. Log it in the hypothesis ledger with a status (OPEN).
  3. Keep a belief-state, not a feeling. Each hypothesis carries: credence (your probability it's real, 0–1), the evidence chain (each test, dated, with the credence delta it caused), and its cheapest next falsifying test. Update the number when evidence lands — both directions.
  4. Attack every streak. Track consecutive credence-raising events with no kill-attempt between them. At 3, stop confirming and run the strongest attack you can design (decay slice, capacity, full-history depth, discriminating test). A streak is a signal to attack, never to size up.
  5. Depth before anointing. Any "winner" found in a short observation window (a performer, a config, a tactic) gets a full-history audit before it becomes evidence — short windows manufacture winners (verified: a candidate that looked strong over ~8 samples reversed hard at depth; a "most consistent" performer was net-negative over its full history).
  6. Kill or promote, in writing. Every hypothesis resolves to a dated verdict with receipts; killed ideas stay on the ledger (they block re-litigation without new evidence). Scope every verdict honestly: "no edge in what we generated" — never "the space is empty."

Read the full file on GitHub · 104 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. 7d ago First seen · 104 lines · 0 tokens per session scan A c4b18af9d87b

Subscribe to this mod's changes

Discovery Loop is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,437 once invoked, about $0.0007 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

happiness-skill

A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.

kangarooking/cangjie-skill · 136 tokens

short-drama-storyboard

A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.

zenstory-ai/drama-skills · 102 tokens

setup-matt-pocock-skills

A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.

devcxl/mattpocock-skills-zh · 43 tokens

frontend-design

A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.

AnastasiyaW/codex-claude-code-config · 264 tokens

alterlab-cobrapy

Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…

AlterLab-IEU/AlterLab-Academic-Skills · 91 tokens

alterlab-depmap

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…

AlterLab-IEU/AlterLab-Academic-Skills · 77 tokens