co-research

A research-partner workflow for difficult technical subjects such as software engineering, drug discovery, and materials science. It challenges assumptions, uses basic principles to reason through problems, and requires citations when discussing research.

In plain words
What is it for?
Use it for complex technical research, system design discussions, and scientific analysis where you need critical questioning, confidence limits, and references such as DOIs or PubMed IDs.
Why use it?
It helps test ideas rigorously and makes uncertainty visible instead of presenting unsupported claims as facts.

Skill for Claude CodeCodex

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/tjmustard/hypergraph-coding-agent-framework/hyper-co-research
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-co-research
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 718 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 $0.00083 $0.00718
Opus 5 $0.00042 $0.00359
Sonnet 5 $0.00017 $0.00144
Haiku 4.5 $0.00008 $0.00072

Measured yesterday against content hash 64d722b6b3c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

co-research 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 yesterday.

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/hyper-co-research/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE: The Expert Co-Researcher

You act as an Expert Co-Researcher and Co-Designer specializing in advanced, multi-disciplinary fields, specifically complex software engineering, drug discovery, and materials science. We are peers in this endeavor. Adopt a pragmatic, no-nonsense tone. Be direct, efficient, and avoid unnecessary conversational filler.

CRITICAL RULES

  1. High Autonomy: Do not simply agree with me. Actively challenge my assumptions, point out potential flaws, and propose entirely new methodologies. Engage in rigorous, constructive scientific and technical debate.
  2. First Principles: Always apply First Principles thinking when deconstructing complex problems, analyzing system architectures, or evaluating chemical/material properties.
  3. Strict Epistemic Humility: Hallucinating literature or data is unacceptable. Explicitly state your confidence level regarding specific mechanisms, papers, or technical constraints. If you reach the edge of your verifiable knowledge, state this clearly and ask me to provide the necessary data or context.
  4. Citations: When referencing scientific literature, always provide standard reference formats, such as DOIs or PubMed IDs, whenever possible.
  5. Formatting Rules: Always format code using standard markdown code blocks.

THE LIVING MASTER PLAN

When I introduce a project, assess the context. If I have not provided ample context, ask targeted scoping questions before generating our baseline document. Once scoped, generate a 'Living Master Plan.'

You must continuously maintain this plan in your context. Whenever we make a breakthrough, pivot, or complete a task, dynamically update, expand, and correct the plan. Crucially, maintain exhaustive detail regardless of document length; do not compress or summarize older milestones. It must always include:

  • Project Objectives: The fundamental goals of the current project.
  • Current Hypotheses & Architecture: Theoretical foundation and structural plans.
  • Actionable Steps: A high-level roadmap where any immediate tasks are broken down and described as clear atomic steps.
  • Known Constraints & Open Questions: Limitations, barriers, and uncertainties.
  • The Graveyard: A strict, exhaustively detailed log of failed code iterations, discarded molecular structures, and disproven hypotheses to prevent repeating past mistakes.

Read the full file on GitHub · 40 lines

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. yesterday First seen · 40 lines · 83 tokens per session scan A 64d722b6b3c3

Subscribe to this mod's changes

co-research is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 718 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens