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 jinleiphys/research_LLM_wiki --skill research-profilegit clone --depth 1 https://github.com/jinleiphys/research_LLM_wikiWrote 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/jinleiphys/research_llm_wiki/research-profile)<a href="https://agentmods.dev/skills/jinleiphys/research_llm_wiki/research-profile"><img src="https://agentmods.dev/badge/skills/jinleiphys/research_llm_wiki/research-profile/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/jinleiphys/research_llm_wiki/research-profile"><img src="https://agentmods.dev/badge/skills/jinleiphys/research_llm_wiki/research-profile.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 | $0.00132 | $0.07206 |
| Opus 5 | $0.00066 | $0.03603 |
| Sonnet 5 | $0.00026 | $0.01441 |
| Haiku 4.5 | $0.00013 | $0.00721 |
Grade B, and why
research-profile scanned grade B with 1 finding 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 11d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Claude Code: `grep -Fxq` for the import line in `~/.claude/CLAUDE.md` first; skip if present, else show diff and ask before appending. How it starts
The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Profile Maintenance (Schema v2)
This file is the canonical operational protocol. It is harness-neutral. The skill ships parallel SKILL.md (Claude Code entry) and AGENTS.md (Codex CLI entry) bodies that mirror each other; if you edit one, edit the other.
Schema v2 (current) introduces controlled vocabulary, tag-driven indexing, AUTO-marker profile sections, and an explicit migrate path from v1. See Migration from v1 below if you have a v1 wiki.
v2.1 addition: bi-temporal timeline: frontmatter for tracked facts that change over time (see "Bi-temporal facts" below). Existing pages adopt it lazily, on the first change to a tracked fact.
Why this skill exists
Memory of "what the user has worked on" should not live only in the user's head and in scattered drafts. It should be a curated, persistent, machine-queryable artifact that:
- Auto-loads into every new agent session, so the assistant starts with full context.
- Captures failures with reasons — research's most common scarring is doing the same dead-end twice. The wiki remembers so the user doesn't have to.
- Makes cross-cutting queries cheap. "What have I done on topic X?" should not require manual grep across years of notes; tag-driven indices answer it in one read.
This is the factual record of what the user has done, not a personality simulator.
Wiki location
Resolution order on every invocation:
RESEARCH_PROFILE_PATHenv var.~/.research-profile-path(single-line absolute path).- Default:
~/research-wiki-personal/.
This wiki is private. Treat the path with notebook-grade care. Recommend a local + private remote git repo. If the directory does not exist, ask before creating.
The auto-load mechanism
The single most important file is <wiki>/profile.md — a one-page summary structured to fit in <2k tokens. It is auto-loaded into every session via your harness's documented mechanism.
What ships with it
6 files 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.
- 11d ago First seen · 476 lines · 132 tokens per session scan B 1a9ed33a3642
research-profile is a skill published in the GitHub repository jinleiphys/research_LLM_wiki (10 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 7,206 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reconcile
Cross-reference a paper against the collection. Finds which cited papers are already collected, which are new leads, which collection papers cite this one, and reconciles all cross-references bidirectionally. Run on a single paper directory or use --all for the entire collection.
adjudicate
Systematically adjudicate disagreements across a paper collection. Produces ruthless verdicts on who was wrong, what supersedes what, and what the best current understanding is. Organized by topic clusters with actionable replacement values for implementation.
author-context
Create a propstore context for one paper with CEL assumptions, parameters, and perspective. Every claim extracted from the paper will reference this context. Required before extract-claims if the paper does not already have one.
author-rules
Author the DeLP rule artifacts (strict, defeasible, properdefeater, blockingdefeater) encoding a paper's stated argument structure. Runs after register-predicates.
extract-claims
Extract propositional claims from a paper directory into the propstore source branch using pks source propose-claim.
paper-retriever
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever- access…