Borrowing it
Nothing to install: this file belongs to jeffbai996/vecgrep. 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/jeffbai996/vecgrep/main/AGENTS.mdgit clone --depth 1 https://github.com/jeffbai996/vecgrepWrote 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/jeffbai996/vecgrep/agents-md)<a href="https://agentmods.dev/instructions/jeffbai996/vecgrep/agents-md"><img src="https://agentmods.dev/badge/instructions/jeffbai996/vecgrep/agents-md/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/instructions/jeffbai996/vecgrep/agents-md"><img src="https://agentmods.dev/badge/instructions/jeffbai996/vecgrep/agents-md.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 | $0.01858 | $0.01858 |
| Opus 5.5 | $0.00743 | $0.00743 |
| Sonnet 5.5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
vecgrep 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 1mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidance and scaling roadmap
Scope and authority
This file governs work in this repository. The scaling roadmap below records the agreed direction as of 2026-09-11; unchecked work is proposed, not shipped. It supersedes the obsolete v0.2/v0.3 build order in CLAUDE.md, not the project's privacy, compatibility, or test requirements. Consult README.md, CHANGELOG.md, CONTRIBUTING.md, docs/DEVELOPING.md, and the implementation for current behavior. Other candidates remain in docs/IDEAS.md.
Keep this public repository generic: no private transcripts, evaluation gold, credentials, internal hostnames, or deployment-specific paths in committed files. Operational observations belong in private deployment records. Preserve the local-first default and stable CLI, HTTP, and MCP contracts.
Objective
Retain an expanding archive while controlling the resident working set and the cost of ordinary queries. Growth should primarily consume disk; a new message should require work proportional to the changed content. Broad historical investigations may spend more time and I/O through an explicit expansion path. Do not promise unlimited data, fixed resources, perfect recall, and fixed latency.
Separate three responsibilities behind the existing vecgrep interface:
- Evidence: canonical permitted content, versions, source references, and history.
- Search: rebuildable lexical, metadata, and semantic indexes with bounded caches.
- Working knowledge: current facts, decisions, and summaries linked to evidence.
The evidence layer must respect source privacy rules; it does not authorize centralizing raw agent logs. Summaries are derived records, never substitutes for original evidence or the sole route to historical details.
Existing work to reuse
Read docs/STORAGE_RETRIEVAL_2026-08.md before proposing a storage or ranking change. It documents payload carriers, disk-backed indexes, embedding cache improvements, retrieval evaluations, and the distinction between quantization and disk savings. Inspect current code and deployed settings because those measurements are dated. Reuse vecgrep.eval and existing source-level quality metrics. Do not recreate the evaluation harness or assume a database replacement is necessary.
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.
- 1mo ago First seen · 170 lines · 1,858 tokens per session scan A d7622f0e5075
vecgrep AGENTS.md is an instructions file published in the GitHub repository jeffbai996/vecgrep (2 stars, last pushed 2d ago), licensed MIT. It adds 1,858 tokens to every session, about $0.0074 per session on Opus 5.5. 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 2026-09-16.
vecgrep AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vecgrep AGENTS.mdjeffbai996/vecgrep | Instructions file | 2 | 2d ago | MIT | A | 1,858 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |