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.
npx skills add rp1-run/rp1 --skill validate-hypothesisgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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.
[](https://agentmods.dev/skills/rp1-run/rp1/validate-hypothesis)<a href="https://agentmods.dev/skills/rp1-run/rp1/validate-hypothesis"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/validate-hypothesis/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.
<a href="https://agentmods.dev/skills/rp1-run/rp1/validate-hypothesis"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/validate-hypothesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.01004 |
| Opus 5.5 | $0.00008 | $0.00402 |
| Sonnet 5.5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
validate-hypothesis 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Validator
Invokes hypothesis-tester agent to validate design assumptions.
Supports two modes:
- Feature-bound (FEATURE_ID provided): validates hypotheses from an existing
hypotheses.mdartifact - Ad-hoc (HYPOTHESIS provided, no FEATURE_ID): validates a free-form hypothesis without feature context
Input Validation
At least one of FEATURE_ID or HYPOTHESIS must be provided. If neither is set:
ERROR: Provide either FEATURE_ID (for feature-bound validation) or --hypothesis "text" (for ad-hoc validation).
Mode Selection
Mode is determined by feature-directory existence, not argument precedence:
- If FEATURE_ID is set AND
{workRoot}/features/{FEATURE_ID}/exists -> feature-bound mode. - If FEATURE_ID is set AND
{workRoot}/features/{FEATURE_ID}/does NOT exist:- If HYPOTHESIS is also populated -> combine as
HYPOTHESIS = "{FEATURE_ID} {HYPOTHESIS}", clear FEATURE_ID -> ad-hoc mode. - If HYPOTHESIS is empty (lone token, no matching directory) -> error:
ERROR: Feature directory not found: {workRoot}/features/{FEATURE_ID}/ For ad-hoc validation, use: --hypothesis "your scenario description"
- If HYPOTHESIS is also populated -> combine as
- If only HYPOTHESIS is set (no FEATURE_ID) -> ad-hoc mode.
Execution
Feature-bound Mode (FEATURE_ID provided)
Prerequisites
{workRoot}/features/{FEATURE_ID}/hypotheses.mdMUST exist- Created by the feature-architect agent during the design phase when high-risk assumptions are identified
Step 1: Invoke Agent
{% dispatch_agent "rp1-dev:hypothesis-tester" %} FEATURE_ID: {FEATURE_ID} Validate all PENDING hypotheses for this feature. {% enddispatch_agent %}
Agent actions: load hypotheses.md -> parse PENDING -> validate via experiment/analysis/research -> document findings w/ evidence -> update status CONFIRMED|REJECTED -> cleanup temp artifacts -> report summary
Step 2: Handle Rejected Hypotheses
Parse agent output. If JSON block w/ type: "rejected_hypotheses":
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.
- 1mo ago First seen · 116 lines · 20 tokens per session scan A 7f8f0e558ab5
validate-hypothesis is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 16d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,004 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-07.
Other skills, from other repositories
[object Object]
Skill "[object Object]" from microsoft/apm, covering what this package does, getting started, available primitives and included workflows.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
openspec-bulk-archive-change
Archive multiple completed OpenSpec changes at once. Use when archiving several parallel changes. Also use for a plural archive request - "openspec bulk-archive", "opsx bulk-archive", "openspec archive all", or "openspec archive these changes".
acceptance-test-authoring
Use when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an acceptance stack, or implementing OpenSpec tasks that involve acceptance tests.
gherkin-authoring
Use when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data Tables, tags, or Gherkin embedded in Markdown.
adversarial-authoring
Use when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or "mixture of models"; coordinates adversarial authoring and review subagents and records council notes.