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/jerrywhites/research-loop/agents-mdgit clone --depth 1 https://github.com/JerryWhites/research-loopWhat 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 | $0.01180 | $0.01180 |
| Opus 5 | $0.00590 | $0.00590 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
research-loop 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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and people) working in this repo. The posting asked for code documented "for people and agents" — this is that file. Read the README for the product story; read this for the map and the contracts you must not break.
What this repo is
research-loop is a Next.js 15 (App Router) app that runs AI-moderated
interviews, auto-analyzes each session into summary/chapters/highlights/tags,
and serves a semantically searchable transcript repository whose answers cite
the exact transcript moment — all also exposed as a 5-tool MCP server, plus an
eval harness. One deployable artifact: UI + API + MCP.
Map — where things live, and the load-bearing contracts
lib/moderator/textLoop.ts— the shared moderator brain.moderatorStep,ModeratorState,initialModeratorState, andstepResponseSchemaare a FROZEN contract: the eval harness (persona-bot ↔ moderator) and the text UI both callmoderatorStep. Don't change its signature or the state shape without updating evals in lockstep.lib/moderator/instructions.ts—buildInstructions(guide, { mode }), the single source of moderator behavior for both voice and text. Pure (no env/db) so it's unit-testable. The probing/neutrality/closing wording is asserted by tests.lib/mcp/tools.ts— the single source of truth for MCP tool defs (names, descriptions, input schemas, handlers). The route (app/api/mcp/route.ts) and the tests both consume it; it imports no Next.js so tests can too.lib/db/queries.ts— all DB access goes through here. Compose existing queries; don't reach into the client elsewhere. The DB is libSQL/SQLite.lib/env.ts— lazy env rule: importing any module must never require a key. OnlyrequireEnv()throws, and only when called. The token-free test suite depends on this; don't read keys at module top level.lib/search/—cosine(pure math),retrieve(searchRepository, brute-force cosine + optional rerank, participant-only by default),ask(askRepository+parseCitationMarkers— every claim must carry a[n]).lib/analysis/analyze.ts— one structured Claude call → summary/chapters/ highlights/tags, then embeddings. Idempotent.
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.
- yesterday First seen · 81 lines · 1,180 tokens per session scan A 8ac117772040
research-loop AGENTS.md is an instructions file published in the GitHub repository JerryWhites/research-loop (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.