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/legann/repovine/agents-mdgit clone --depth 1 https://github.com/legann/repovineWrote 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/legann/repovine/agents-md)<a href="https://agentmods.dev/instructions/legann/repovine/agents-md"><img src="https://agentmods.dev/badge/instructions/legann/repovine/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 | $0.01325 | $0.01325 |
| Opus 5 | $0.00662 | $0.00662 |
| Sonnet 5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
repovine 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 3d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repovine -- quick reference
This managed block is intentionally short for Claude Code and Codex. Detailed workflows live in the generated skills, agent files, and hooks so this always-on file does not compete with project instructions.
Start
Before non-trivial work, call the repovine MCP server first. Use search_context when the task wording is fuzzy, map_context when a domain/package/module is named, then inspect_node after narrowing. Skip this only for trivial single-file tasks.
If the MCP call fails with a connection error, the server is not running. Ask the user to check the MCP config. Do not fall back to blind file reading -- without the graph you lack structure and dependency info.
If a tool returns result.status:"building", call get_build_status({ "waitSec": 45 }) once instead of polling. stageEtaSec estimates only the current stage; use stage and remainingStages to report progress. If the long-poll still returns building, continue with direct file reads only when the task can proceed without graph structure. To abandon a cold build, call get_build_status({ "cancel": true }); it stops Stage 1 workers and returns cancelled (no graph) or keeps a prior ready graph.
Context Session Quality scores repovine MCP responses, not agent prose. Pass contextSessionId on MCP calls and inspect with get_context_session_quality; harnesses recompute via repovine delivery compliance. The score and its thresholds are advisory until the labelled-corpus return bar in docs/context-quality.md is met; evidence-backed annotation checks remain enforceable.
Working loop
- Orient/map/inspect:
search_context,map_context,inspect_node. - Follow the task axis: runtime/user flow ->
get_entrypoints+trace_flow; shared contracts ->analyze_dependencies; env/resources ->get_config_surface; architecture/review candidates ->analyze_architecture; annotation health ->get_annotation_status. - After code edits, call
refresh_context({}). After changingrepovine.config.json, callrefresh_context({ "reloadConfig": true })so the running MCP process re-reads config and rebuilds the graph. Changingrepovine.domains.jsonis picked up by a normal refresh; usingreloadConfig: trueis harmless when both files changed. - Never hand-edit
repovine.annots.json. Change it throughwrite_annotation,merge_annotations, orrefresh_context({ "cleanupOrphans": true });validate_annotationsreads it and reports, and writes nothing.
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.
- 3d ago First seen · 68 lines · 1,325 tokens per session scan A 3d9121bae0a0
repovine AGENTS.md is an instructions file published in the GitHub repository legann/repovine (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,325 tokens to every session, about $0.0066 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
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).
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.
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.