Borrowing it
Nothing to install: this file belongs to vantasnerdan/substrate-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vantasnerdan/substrate-framework/main/.agents/skills/research-pr-harvest/SKILL.mdgit clone --depth 1 https://github.com/vantasnerdan/substrate-frameworkWrote 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/vantasnerdan/substrate-framework/research-pr-harvest)<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/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/vantasnerdan/substrate-framework/research-pr-harvest"><img src="https://agentmods.dev/badge/skills/vantasnerdan/substrate-framework/research-pr-harvest.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 | $0.00065 | $0.01519 |
| Opus 5.5 | $0.00026 | $0.00608 |
| Sonnet 5.5 | $0.00013 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
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 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research PR Harvest
The elite harvest lands the strongest useful positive statement with the minimum truthful repair. Keep three decisions separate: artifact merge, scientific claim promotion, and whole-goal completion. Provenance and reuse are valuable; they acquire accepted scientific authority through governance, not by merging.
Apply AGENTS.md for the reward, terminal campaign, ownership, and review
contract. This skill serves existing external PRs or terminal campaign PRs;
active local campaigns preserve intermediate utilities and subclaims as branch
commits while continuing their parent objective.
Achievement 1 — a clear, authorized boundary
Read the PR, goal issue, base release, accepted scope, diff, tests, and discussion.
Load physics-erdos-loop for physics and the applicable code-review/impact
workflow. Use current GitNexus or AST/source analysis for changed symbols and
consumers; independently reason about the science and omitted alternatives.
Identify exactly one canonical issue that predates even the draft PR.
Use Advances #N for incomplete higher goals and Fixes #N for full success.
For an external PR missing that issue, create it, preserve the original PR as
provenance, and open a compliant focused harvest afterward.
A user-supplied PR authorizes a non-author/non-implementer agent to process its normal lifecycle: review/comment, metadata, corrections, focused harvest, eligible merge, qualified closure, and issue update. Use a distinct merger by default. The user or repository owner may explicitly direct an authoring agent to self-merge a named PR; record the override separately from independent scientific review. Preserve contributor history, unrelated branches, the user's objective, and promotion boundaries. Report an actual permission/protection barrier with the exact next action rather than assuming broader authority.
Achievement 2 — useful units and minimum repairs
Group independently mergeable units or materially different risks, not every file or theorem entrypoint. Examples: utility, exact identity, solver/verifier, conditional component, speculative composition, or a reviewed durable narrative. Record each unit's statement, dependencies, evidence, consumers, and usefulness without the favored headline.
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.
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 Changed · +2 lines fd28bcd3fdd3
- 1mo ago Changed · -118 lines · -22 tokens per session 4f32446dcc01
- 2mo ago First seen · 248 lines · 87 tokens per session scan A b0b4961d9200
research-pr-harvest is a skill published in the GitHub repository vantasnerdan/substrate-framework (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,519 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…