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 agentmods add instructions/haowenhou/agenticresearchwiki/agents-mdgit clone --depth 1 https://github.com/HaowenHou/AgenticResearchWikiWrote 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/instructions/haowenhou/agenticresearchwiki/agents-md)<a href="https://agentmods.dev/instructions/haowenhou/agenticresearchwiki/agents-md"><img src="https://agentmods.dev/badge/instructions/haowenhou/agenticresearchwiki/agents-md.svg" alt="Measured on agentmods" 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 | $0.00418 | $0.00418 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
AgenticResearchWiki AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- AgenticResearchWiki CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Reading docs
This repo is a documentation repo that records everything about this research project: background, goals, methods, experiments, paths, data, etc.
Links between docs use wiki-style [[ ]] syntax.
When you need to answer questions, make changes, or update project docs for this research project, first gather the necessary information from this wiki.
Reading order
- [[Overview]] — project background, goals, methods, task navigation, experimental side tracks
- Pick based on task type:
- Data task -> [[DataOverview]]
- Training task -> [[TrainingOverview]]
- Eval task -> [[EvalOverview]] Read the docs selectively and hierarchically based on my task.
Do NOT read by default
- Historical docs under
**/Archived/ - Abandoned track docs under
ExperimentalTracks/abandoned/, unless the task explicitly asks to "review / post-mortem an abandoned plan" - Long experiment logs, unless the current task explicitly requires tracing back
ResearchNotes/holds background research, comparison, and notes-style docs. These are primarily for human understanding and decision-making and are NOT default task entry points. Only when the task explicitly asks for "research / comparison / reviewing the decision rationale", enter via [[ResearchNotesOverview]] and read on demand.
Template placeholders
{{...}} in docs are unfilled template fields (the text inside the braces is a fill hint). Do not treat them as real content or base any judgment on them. When you see one:
- If the task needs the real value of that field: ask the user first, then fill it in and remove the braces after they reply;
- If the task is to fill in the doc: generate content following the hint inside the braces, replacing the entire
{{...}}; - When writing records back / tidying docs: do not keep or add new
{{...}}, unless it's deliberately left as a placeholder for the user.
Doc-update rules
Invoke the corresponding doc-update skill.
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.
- 5d ago First seen · 28 lines · 418 tokens per session scan A 990eefd57691
AgenticResearchWiki AGENTS.md is an instructions file published in the GitHub repository HaowenHou/AgenticResearchWiki (29 stars, last pushed 5mo ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
Puppetmaster AGENTS.md
AGENTS.md instructions for professorpalmer/Puppetmaster, covering agents.md, first: are you a puppetmaster worker?, default subagent runtime: puppetmaster, when to start a puppetmaster swarm (do this by default) and match the verb to the task shape (single feature ≠ swarm).
agentic-playwright config.instructions.md
Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
hatch3r CLAUDE.md
Claude Code instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).