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/savant0x/savant-code/agents-mdgit clone --depth 1 https://github.com/savant0x/savant-codeWhat 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 | $0.01530 | $0.01530 |
| Opus 5 | $0.00765 | $0.00765 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
savant-code 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Savant-Code
Savant-Code is the multi-agent AI coding assistant built on the ECHO Protocol v0.2.0.
All work is governed by ECHO Protocol. No code is written without a FID that has converged through the Perfection Loop.
Key Technologies
- TypeScript monorepo (
strict: true,noImplicitReturns: true) - Bun runtime + package manager (≥ 1.3.11; root pins
1.3.14perengines.bun) - OpenTUI + React CLI (
@opentui/core0.5.3,react^19) - JS/TS SDK — embeddable via
SavantClient - Composable agent runtime — ECHO 10-agent roster with separation of duties
- ECHO Protocol v0.2.0 — single bootstrap file
Agent Roster (10 canonical ECHO roles)
The 10-agent roster is enforced in ARCHITECTURE.md. Each agent has restricted tools. See
ARCHITECTURE.md → "Helper Tool Libraries" for the distinction between the 10 runtime roles and the
filesystem entries in agents/.
| Agent | Phase | Role |
|---|---|---|
| Orchestrator | ALL | Routes work, enforces protocol, spawns agents |
| Detective | RED | Codebase analysis + grep call-graphs |
| Forge | GREEN | Implementation only — writes code from converged FID |
| Verifier | AUDIT | Double-audit, run tests, check call-graph, cite file:line evidence |
| Recorder | FID | Create, track, archive FIDs. Update CHANGELOG. |
| Thinker | Planning | Sequential reasoning via sequentialthinking tool |
| Scout | Explore | Glob/list_directory/read_files for context gathering |
| Researcher | Research | Web search + docs lookup |
| Scribe | Docs | Session summaries, LESSONS.md, knowledge files |
| Adversary | ADVERSARIAL | Meta-verification: refutes Verifier FAILs, re-audits unevidenced PASSes, verdicts override (FID-2026-0805-004) |
Repo Map
| Workspace | Package | Purpose |
|---|---|---|
agents/ |
@savant-code/agents |
Public agent definitions shipped with the CLI (10 canonical + 6 helper tool-library/trace dirs) |
cli/ |
@savant-code/cli |
CLI source — UI, commands, state, hooks, OpenTUI/React components |
common/ |
@savant-code/common |
Shared types, tool definitions, utilities |
evals/ |
@savant-code/evals |
Eval benchmark runner + public eval fixtures |
savant-free/ |
@savant-code/savant-free |
CLI release + e2e tests for the free variant |
packages/database/ |
@savant-code/database |
Database abstraction layer |
packages/agent-runtime/ |
@savant-code/agent-runtime |
Agent loop, tool executor, LLM API integration |
packages/code-map/ |
@savant-code/code-map |
tree-sitter code indexing, language detection |
packages/knowledge-graph/ |
@savant-code/knowledge-graph |
Deterministic codebase knowledge-graph engine (indexer, queries, clustering, export serializer) |
packages/llm-providers/ |
@savant-code/llm-providers |
Public LLM provider shims |
sdk/ |
@savant-code/sdk |
Public SDK — SavantClient, types, build + verify scripts |
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.
- 2d ago First seen · 103 lines · 1,530 tokens per session scan A d5db646ae0c4
savant-code AGENTS.md is an instructions file published in the GitHub repository savant0x/savant-code (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,530 tokens to every session, about $0.0076 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
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.