Borrowing it
Nothing to install: this file belongs to Vbj1808/retrieval-lens. 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/Vbj1808/retrieval-lens/main/AGENTS.mdgit clone --depth 1 https://github.com/Vbj1808/retrieval-lensWrote 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/vbj1808/retrieval-lens/agents-md)<a href="https://agentmods.dev/instructions/vbj1808/retrieval-lens/agents-md"><img src="https://agentmods.dev/badge/instructions/vbj1808/retrieval-lens/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 | $0.00737 | $0.00737 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
retrieval-lens 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — retrieval-lens
retrieval-lens is a TypeScript MCP server that intercepts RAG retrieval calls, logs every chunk seen by the model (with scores, query, timestamp, and source), and exposes tools so agents can audit, replay, and diff retrieval runs.
First-Run Commands
npm install # install dependencies
npm run build # compile TypeScript → dist/
npm test # run full test suite (vitest)
npm run lint # eslint + tsc --noEmit
npm run inspect # run mcp-inspector against built server
If any of these fail, fix that before writing new feature code.
Startup Workflow (read this every session)
pwd— confirm you are in the project root.- Read
PROGRESS.md— find the current verified state and the single next task. - Read
feature_list.json— identify the highest-priority feature with status"pending". git log --oneline -5— understand what the last session completed.npm install && npm run build && npm test— verify baseline is green.- If baseline is red, fix it first. Do not start new work on a broken state.
Hard Constraints
- WIP = 1. Work on exactly one feature per session. Do not activate a second task.
- No
console.loginsrc/— use theloggerutility insrc/utils/logger.ts. - No
anytypes — TypeScript strict mode is on; every type must be explicit. - No direct SQLite calls outside
src/db/— all storage goes through the db module. - MCP schema validity is non-negotiable — every tool must pass
npm run inspectbefore marking done. - Do not modify
package.jsonscripts ortsconfig.jsonwithout an explicit instruction. - Do not declare a feature done unless all Definition of Done criteria are met (see below).
Definition of Done (per feature)
A task is complete only when ALL of the following are true:
- Implementation exists in
src/ -
npm testpasses with 0 failures -
npm run lintpasses with 0 errors -
npm run inspectlists the tool with correct input/output schema - Coverage for the new module is ≥ 85%
-
PROGRESS.mdis updated with evidence (test output line, not just "done") -
feature_list.jsonstatus updated to"complete" -
git commitmade with message format:feat(<tool-name>): <what it does>
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.
- 7d ago First seen · 66 lines · 737 tokens per session scan A 75ac2cfc71c4
retrieval-lens AGENTS.md is an instructions file published in the GitHub repository Vbj1808/retrieval-lens (2 stars, last pushed 3mo ago), licensed MIT. It adds 737 tokens to every session, about $0.0037 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
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.