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/scarletkc/vexor/agents-mdgit clone --depth 1 https://github.com/scarletkc/vexorWrote 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/scarletkc/vexor/agents-md)<a href="https://agentmods.dev/instructions/scarletkc/vexor/agents-md"><img src="https://agentmods.dev/badge/instructions/scarletkc/vexor/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 | $0.00985 | $0.00985 |
| Opus 5 | $0.00492 | $0.00492 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
vexor 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Non-negotiables
- Run Python commands inside the repository's existing virtual environment. Create
.venvonly when none exists; never install into the system interpreter. - Fix root causes. Do not swallow errors or add silent fallbacks. A degraded path is acceptable
only when it is deliberate and user-visible. When the root cause stays unclear, say so and name
the missing information; extending
vexor doctoror verbose output beats a speculative fix. - Ask when requirements are ambiguous or inconsistent instead of inventing behavior. Do not ship temporary, placeholder, or demo-only implementations unless explicitly requested.
- Never commit API keys, private endpoints, or local credentials. Store them via Vexor's config
commands, provider environment variables, or a git-ignored
.env.
Project map
vexor/contains the runtime,vexor/services/the orchestration layer (including the MCP stdio server inmcp_service.py, exposed viavexor mcp), andvexor/providers/the provider adapters and capability metadata. Thevoyageaiandcustomproviders route through the OpenAI-compatible adapter instead of dedicated modules.- Tests mirror the product surface under
tests/unit/andtests/integration/. Documentation lives indocs/;docs/roadmap.mdis the source of truth for priorities, and the README stays lean and links intodocs/. plugins/vexor/skills/vexor-cli/SKILL.mdis the bundled standalone agent guide. Check it when commands or behavior change.
Implementation
- Follow PEP 8 with 4-space indentation and roughly 100-character lines. Type-annotate new code and keep Typer command names lowercase and imperative.
- Route user-facing CLI copy through
vexor/text.py. Reuse the services layer, structured output paths, and shared helpers before adding new logic; extract the smallest useful helper when behavior is duplicated. - Use
typer.BadParameterfor CLI validation where appropriate. Keep human and porcelain output separate, and treat machine-readable output as a compatibility contract. - Treat filesystem paths, extracted content, embedding payloads, and provider or reranker responses as untrusted input.
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 · 71 lines · 985 tokens per session scan A e01a8d86befb
vexor AGENTS.md is an instructions file published in the GitHub repository scarletkc/vexor (239 stars, last pushed 6d ago), licensed MIT. It adds 985 tokens to every session, about $0.0049 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
cs CLAUDE.md
Claude Code instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
Xapiand AGENTS.md
Instructions for Kronuz/Xapiand, covering agents.md — working in the xapiand codebase, first, the big split: own code vs. vendored, where things live, build & toggles and verifying changes end-to-end (the docs are a test suite).
ketch CLAUDE.md
Claude Code instructions for 1broseidon/ketch, covering ketch, architecture, build & test, output format and output flags (all commands).
litellm-rs AGENTS.md
AGENTS.md instructions for majiayu000/litellm-rs, covering agents.md, workflow, commands and rules.
dense-mem AGENTS.md
AGENTS.md instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.
codesage AGENTS.md
AGENTS.md instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.