sonde: Instructions file for Codex

AGENTS.md

sonde AGENTS.md is an instructions file for Codex, OpenCode from anishmoncivarghese/sonde. It costs 1,889 tokens per session, scanned A, original, Apache-2.0.

Um conjunto de instruções para agentes que trabalham no projeto Sonde, uma ferramenta que analisa relações entre partes do código. Ele orienta como recuperar o histórico, registrar decisões e passar o trabalho para outro agente.

In plain words
What is it for?
Serve para iniciar sessões com o estado do projeto, documentar escolhas durante revisões ou alterações e preparar transferências de trabalho entre agentes.
Why use it?
Evita que um agente comece sem conhecer o estado atual do projeto ou perca as razões por trás das decisões. Também reduz o risco de trabalho interrompido ficar sem contexto.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is anishmoncivarghese/sonde's own configuration. It tells Codex and OpenCode how to work on sonde itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sonde configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anishmoncivarghese/sonde. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/anishmoncivarghese/sonde/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/anishmoncivarghese/sonde

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for sonde AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anishmoncivarghese/sonde/agents-md.svg)](https://agentmods.dev/instructions/anishmoncivarghese/sonde/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/anishmoncivarghese/sonde/agents-md"><img src="https://agentmods.dev/badge/instructions/anishmoncivarghese/sonde/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,889 This file is loaded in full into every session.
When invoked 1,889 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01889 $0.01889
Opus 5 $0.00945 $0.00945
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 8d ago against content hash 5e821f4726fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sonde 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 8d 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.

AGENTS.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project history

At the start of a session, before touching code, run:

whyline sync

That prints the active handoff, Git state, ownership warnings, and relevant decisions. Do not ask permission. If it reports no handoff or history, say so in your first message, so the human knows the context is empty rather than unread.

Recording decisions

After completing any non-trivial change, or after reviewing someone else's, record the reasoning:

whyline note "<one-line decision>" \
  --because "<why this choice>" \
  --rejected "<option>: <why not>" \
  --file <path> \
  --actor <agent> --role <role> --task <task-id>

Reviewing counts as deciding. Ruling a defect worth fixing now, accepting a deviation from the plan, or judging a risk acceptable are all decisions. Record them even though someone else wrote the code, and even if you also logged them in a tracker of your own.

Record only genuine choices a future reader would wonder about. Skip typos, formatting and renames. --rejected is repeatable. Do not ask permission.

Handing off active work

Before another agent takes over, record an explicit handoff with whyline handoff <task-id> --from <agent> --to <agent> --status <status>. Include the changed files, tests and results, open risks or questions, and a short summary.

Sonde

A local code-context engine for AI coding agents. It indexes a repository into a symbol-level graph in SQLite and exposes three MCP tools so an agent can ask structural questions text search cannot answer: who calls this, what breaks if I change it, which tests touch it. TypeScript, Python and Swift. Python requires --resolve, which drives a bundled pyright; its tree-sitter-only tier measured far past the project's unresolved ceiling and is not fit for structural queries.

Picking up this project (any agent, any vendor)

This file carries stable rules only. Current state is deliberately not copied here, because a hand-maintained status section goes stale and then lies. Read it from these instead:

Read the full file on GitHub · 167 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.

  1. 8d ago First seen · 167 lines · 1,889 tokens per session scan A 5e821f4726fe

Subscribe to this mod's changes

sonde AGENTS.md is an instructions file published in the GitHub repository anishmoncivarghese/sonde (3 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,889 tokens to every session, about $0.0094 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.

Related

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.

study8677/repobrain · 229 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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 · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens