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/jarvis-intelligence/jarvis/agents-mdgit clone --depth 1 https://github.com/jarvis-intelligence/jarvisWrote 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/jarvis-intelligence/jarvis/agents-md)<a href="https://agentmods.dev/instructions/jarvis-intelligence/jarvis/agents-md"><img src="https://agentmods.dev/badge/instructions/jarvis-intelligence/jarvis/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 | $0.02927 | $0.02927 |
| Opus 5 | $0.01463 | $0.01463 |
| Sonnet 5 | $0.00585 | $0.00585 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade A, and why
jarvis 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Contributor guide for jarvis — a local-first code intelligence MCP server
(SCIP navigation + Zoekt search). The distribution is published as
jarvis-mcp; the import package, both CLIs, and the MCP server
are all jarvis.
Project Structure & Module Organization
src/jarvis/ — one module per concern:
index_cli.py— thejarvisCLI (subcommandsindex/list/status/reindex/forget/watch) and the indexing pipeline: detect language → run the matching SCIP indexer →scip expt-convert→ populate graph →zoekt-index→ atomic pointer-swap publish.server.py— MCP stdio server (FastMCP) wrappingQueryService/ZoektLifecycle/GraphStore; registers 9 tools.query.py+index_reader.py— SCIP navigation (go-to-definition, find-references, call/type hierarchy, document symbols) as raw SQL against thescip expt-convertschema.index_reader.pyis the read-only SQLite connection cache keyed on the vendored 3-tuple(project, repo, branch).search.py—searchCodevia anhttpxclient to a lazily-spawnedzoekt-webserver;ZoektLifecycleowns the pidfile/health-check/exit-kill — never spawn the webserver elsewhere.graph.py+registry.py— two SQLite stores over~/.jarvis/registry.db.graph.pyis the package dependency graph (packages/edges) drivingblastRadius(2-hop BFS);registry.pyis the repo registry (repostable).semantic.py+chunker.py+embeddings.py— optional semantic path: tree-sitter chunking → sentence-transformers embeddings → per-repo LanceDB table;semanticSearchfuses vector hits with Zoekt hits via reciprocal rank fusion.scip_decoder.py— isolation seam, the only module that importsscip_pb2orzstandard.scip_pb2.py— vendored gencode (regenerated fromscip.protoat tag v0.9.0); do not hand-edit.config.py— data-dir / repo-slug / index-path resolution; single-tenant pinning (PROJECT = "_",BRANCH = "_").models.py— frozen dataclasses for nav-tool result shapes.watch.py—Debouncer(pure, thread-free, fake-clock testable) +should_ignore_path.
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.
- 4d ago First seen · 106 lines · 2,927 tokens per session scan A 00f4b8d99797
jarvis AGENTS.md is an instructions file published in the GitHub repository jarvis-intelligence/jarvis (0 stars, last pushed 12d ago), licensed MIT. It adds 2,927 tokens to every session, about $0.0146 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
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
repobrain AGENTS.md
AGENTS.md instructions for study8677/repobrain: Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Flat is better than nested. Sparse is better than dense. Readability counts. Special cases aren't special enough to break the rules.…
CodeNib AGENTS.md
AGENTS.md instructions for sysevol-ai/CodeNib, covering agents.md, layered objectives, storage scope guard, dev commands and git, commit, and pr rules.
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.
sourcebot CLAUDE.md
Claude Code instructions for sourcebot-dev/sourcebot, covering claude code guidelines, database migrations, building packages, backend workloads and execution locks.
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.