What is tessera AGENTS.md?

A project instruction file for Tessera, an open-source Python tool that gives coding agents persistent memory of a codebase using SQLite, a small database file.

Guiding development of Tessera's code, including its database, code scanner, command-line tool, MCP server, dashboard and optional features.

It records the project's structure, fixed design choices and development rules so agents can work with the repository consistently.

tessera AGENTS.md — Instructions file by dr-code

Install

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.

agentmods

npx agentmods add instructions/dr-code/tessera/agents-md

Clone the repo

git clone --depth 1 https://github.com/dr-code/tessera

Made for: Codex, OpenCode.

Per session 1,388 This file is loaded in full into every session.

When invoked 1,388 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01388	$0.01388
Opus 5	$0.00694	$0.00694
Sonnet 5	$0.00278	$0.00278
Haiku 4.5	$0.00139	$0.00139

Measured yesterday against content hash 6ad679b4d22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tessera 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 yesterday.

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.

AGENTS.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tessera — AGENTS.md

Project Overview

Tessera is an open-source Python MCP server + CLI giving Codex persistent codebase memory via SQLite. No license gating.

Architecture

src/tessera/core/ — SQLite DB, migrations, feature flags
src/tessera/graph/ — scanner, symbol parser, builder, scorer
src/tessera/mcp/ — MCP server (stdio), 10 tools, turn state
src/tessera/debate/ — engine, codex wrapper, Codex wrapper, DLP sanitizer, XML payload
src/tessera/plans/ — plan archive (DB + disk)
src/tessera/compliance/ — git diff vs plan targets
src/tessera/handoff/ — session handoff generator
src/tessera/dashboard/ — Flask dashboard, localhost:5050
src/tessera/cli.py — Click CLI entry point

Key Decisions (locked)

Storage: SQLite with WAL mode, not JSON files
MCP transport: stdio only (dashboard is a separate HTTP process)
Debate: GPT (Codex CLI subprocess) → Codex critique → GPT respond → Codex synthesize
Feature flags: TESSERA_ENABLE_DEBATE, TESSERA_ENABLE_DASHBOARD, TESSERA_ENABLE_COMPLIANCE
Core install (no debate deps): zero remote calls, no API keys needed

Development

# Install in editable mode with all optional deps
pip install -e ".[all]"

# Run tests
pytest tests/

# Run specific test file
pytest tests/test_database.py -v

# Scan tessera itself (dogfood)
tessera scan .

DB Location

.tessera/tessera.db in the project root.

Non-Negotiable Rules

Never hardcode API keys or secrets
Never commit .env files
All write operations go through _retry_write for lock resilience
All file rewrites use atomic os.replace() pattern
DLP sanitizer runs on all content going to external APIs

Critical Rules

0. NEVER Publish Sensitive Data

NEVER commit passwords, API keys, tokens, or secrets to git
NEVER commit .env files — ALWAYS verify .env is in .gitignore
Before ANY commit: verify no secrets are included
NEVER output secrets in suggestions, logs, or responses

3. Testing

Minimum 3 assertions per test
Explicit success criteria only — "it works" is not a criterion

Read the full file on GitHub · 139 lines

Changes

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.

yesterday First seen · 139 lines · 1,388 tokens per session scan A 6ad679b4d22f

Subscribe to this mod's changes

tessera AGENTS.md is an instructions file published in the GitHub repository dr-code/tessera (1 stars, last pushed 21d ago), licensed MIT. It adds 1,388 tokens to every session, about $0.0069 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.

Analytics and metrics Databases Memory and context

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

tessera AGENTS.md