researchforge-validate

researchforge-validate is a skill for Claude Code, Codex from forger-labs-hq/researchforge. It costs 44 tokens per session (385 once invoked), scanned A, original, Apache-2.0.

A repeated benchmark process for checking whether an experiment result holds up across multiple runs. A benchmark is a fixed test used to measure software or model performance.

In plain words
What is it for?
Re-run the full benchmark for finalist experiments, report each measurement and its spread, and label the result validated only when it meets the required checks.
Why use it?
One successful run can be a lucky result; repeated tests reveal variation and show whether constraints hold consistently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Re-run the full benchmark for finalist experiments, report each measurement and its spread, and label the result validated only when it meets the required checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forger-labs-hq/researchforge/researchforge-validate
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 forger-labs-hq/researchforge --skill researchforge-validate
Clone the repo
git clone --depth 1 https://github.com/forger-labs-hq/researchforge

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 researchforge-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-validate.svg)](https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-validate)
Your own site
<a href="https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-validate"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 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 $0.00044 $0.00385
Opus 5 $0.00022 $0.00192
Sonnet 5 $0.00009 $0.00077
Haiku 4.5 $0.00004 $0.00038

Measured 8d ago against content hash fecfd7e55257, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

researchforge-validate 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 8d 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.

src/researchforge/claude/skills/researchforge-validate/SKILL.md · 42 lines

What it actually says

Validate finalists

"Validated" is a structural claim in ResearchForge: it requires the full benchmark plus the contract's configured number of repeated validation runs. A one-off result can never be called validated — the engine enforces this, and so should your language.

Validation repeats the full benchmark, so it costs real time. Tell the user how many repeats the contract configures, get their go-ahead in chat, then:

researchforge validate <run-id> --json

(The command asks for a typed confirmation; only pass --yes if the user explicitly approved validation in this conversation.)

Afterwards, report from the JSON:

  • per-attempt measurements and their spread (mean/stdev) — repeated runs exist precisely to expose variance, so show it;
  • whether hard constraints held on every attempt;
  • the final status: an experiment that survives becomes validated; one that regresses stays honest too — report that as the finding it is.

Next: the researchforge-ship skill turns a validated winner into a clean branch, report, and optional draft PR.

Rules

  • The Python engine is the boundary: never work around a validation error, a protected path, or an approval gate — fix the artifact or ask the user.
  • Approvals belong to the user: never pass --yes or type a confirmation unless the user explicitly approved that step in this conversation.
  • Ground every summary in stored data: quote only numbers returned by --json output or files under .researchforge/ — never invent metrics.
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. 8d ago First seen · 42 lines · 44 tokens per session scan A fecfd7e55257

Subscribe to this mod's changes

researchforge-validate is a skill published in the GitHub repository forger-labs-hq/researchforge (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 44 tokens to every session and 385 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.