research-pr-harvest

research-pr-harvest is a skill for Codex from vantasnerdan/substrate-framework. It costs 87 tokens per session (3,230 once invoked), scanned A, original, Apache-2.0.

A review workflow for research pull requests, which are proposed code changes shared for review. It decides separately whether useful work should be merged, whether a scientific claim is supported, and whether the larger research goal is complete.

In plain words
What is it for?
Use it to assess externally supplied research pull requests and preserve valuable utilities, subclaims, route results, and validation records.
Why use it?
It prevents merging reusable code or intermediate results from being mistaken for proof of a scientific claim or completion of the whole project.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

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/vantasnerdan/substrate-framework/research-pr-harvest
Any agent
npx skills add vantasnerdan/substrate-framework --skill research-pr-harvest
Clone the repo
git clone --depth 1 https://github.com/vantasnerdan/substrate-framework

Made for: 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 research-pr-harvest

README.md
[![agentmods](https://agentmods.dev/badge/skills/vantasnerdan/substrate-framework/research-pr-harvest.svg)](https://agentmods.dev/skills/vantasnerdan/substrate-framework/research-pr-harvest)
Your own site
<a href="https://agentmods.dev/skills/vantasnerdan/substrate-framework/research-pr-harvest"><img src="https://agentmods.dev/badge/skills/vantasnerdan/substrate-framework/research-pr-harvest.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,230 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 5.1 $0.00087 $0.03230
Opus 5 $0.00044 $0.01615
Sonnet 5 $0.00017 $0.00646
Haiku 4.5 $0.00009 $0.00323

Measured 5d ago against content hash b0b4961d9200, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-pr-harvest 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 5d 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.

.agents/skills/research-pr-harvest/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research PR Harvest

Review for durable value, not only for headline victory. Keep three decisions independent:

  1. Artifact merge: is a locally complete unit worth owning?
  2. Claim promotion: has a scientific statement earned accepted authority?
  3. Goal completion: has the whole campaign objective been achieved?

An externally supplied PR may merge useful progress while its claims remain proposed and its goal issue remains open. A terminal-exhaustion campaign PR may likewise preserve its strongest supported units while the positive objective stays open. A merge establishes provenance and availability, not scientific truth; this rule never opens an active campaign's PR gate.

Harvest is not an active-campaign boundary

This skill answers the artifact-merge question for an existing PR or a campaign whose terminal PR gate has already opened. It does not authorize an active campaign executor to create a partial PR. Finding, correcting, or merging a reusable unit does not exhaust a scientific rung, establish or refute the parent question, or satisfy the campaign done gate.

Keep intermediate utilities, subclaims, route verdicts, and validation receipts as coherent commits and append-only attempts on the campaign branch. Open one campaign PR only after the complete positive contract passes or AGENTS.md's scientific-exhaustion certificate passes. “Merge and hand off” is an operational disposition for an existing PR, never a scientific stopping condition.

Establish the boundary

Read the PR, linked goal, base release, accepted claim boundary, diff, tests, and review discussion. For physics work, also load physics-erdos-loop; for code impact, use the available PR-review or dependency-graph workflow.

Identify one canonical goal issue and confirm that it existed before the PR was submitted, including before a draft PR. The PR must mention that issue explicitly: use Advances #N for a terminal exhaustion campaign or another incomplete higher goal and reserve Fixes #N for full positive completion. If an externally supplied source PR has no pre-existing issue, do not merge it. Create the canonical issue, preserve the source PR as provenance, and place any selected units in a new compliant harvest PR opened after the issue. This repair path applies to an already existing external PR; it does not open the PR gate for an active campaign.

Read the full file on GitHub · 248 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. 5d ago First seen · 248 lines · 87 tokens per session scan A b0b4961d9200

Subscribe to this mod's changes

research-pr-harvest is a skill published in the GitHub repository vantasnerdan/substrate-framework (3 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 3,230 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens