sophia AGENTS.md

sophia AGENTS.md is an instructions file for Codex, OpenCode from Kevandrew/sophia. It costs 514 tokens per session, scanned A, original, MIT.

Repository instructions for Sophia, a Go command-line tool that manages change requests, tasks, reviews, and merges through Git.

In plain words
What is it for?
Use them when working on Sophia: switch to the right change-request branch, define work contracts, build and test the code, and handle stale workflow state.
Why use it?
They give an agent the project’s rules, code layout, workflow steps, and checks to run, reducing mistakes and inconsistent changes.

Instructions file for CodexOpenCode

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

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/kevandrew/sophia/agents-md
Clone the repo
git clone --depth 1 https://github.com/Kevandrew/sophia

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 sophia AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kevandrew/sophia/agents-md.svg)](https://agentmods.dev/instructions/kevandrew/sophia/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kevandrew/sophia/agents-md"><img src="https://agentmods.dev/badge/instructions/kevandrew/sophia/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 514 This file is loaded in full into every session.
When invoked 514 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00514 $0.00514
Opus 5 $0.00257 $0.00257
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 6d ago against content hash 4655f133e4d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sophia 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 6d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Sophia is a Go CLI for intent-first change-request workflow over Git.

Start Here

  • Repo map: docs/index.md
  • Agent setup: docs/agent-quickstart.md
  • First-success walkthrough: docs/getting-started.md
  • Daily author loop: docs/workflow.md
  • Recovery and stale-state handling: docs/troubleshooting.md
  • Policy details: docs/repository-policy.md

Build And Verify

  • go run ./cmd/sophia <command> runs the CLI locally.
  • go build ./cmd/sophia builds the entrypoint.
  • go test ./... runs the test suite.
  • go vet ./... runs static checks.

Workflow Invariants

  • Use Sophia as the primary workflow interface for CRs, tasks, review, and merge state.
  • Work on the active CR branch, usually via sophia cr switch <id>.
  • Set the CR contract before implementation and set each task contract before task done.
  • Use explicit checkpoint scope on sophia cr task done; prefer --from-contract when scope is accurate.
  • For agent-created checkpoints, always pass --commit-type <type>.
  • This repo uses merge.mode=pr_gate; do not open/sync PRs or push remote state unless explicitly asked.
  • Delegated child CRs may complete before the parent; the parent remains blocked until child work is resolved.

Codebase Map

  • internal/cli: Cobra wiring, help text, JSON/text output.
  • internal/service: workflow logic, status/review/merge behavior.
  • internal/gitx: Git integration helpers.
  • internal/store, internal/model: persistence and types.

Coding And Tests

  • Format edited Go files with gofmt.
  • Keep file names capability-based and identifiers descriptive.
  • Add focused Go tests near the code you change.
  • Minimum local check before handoff: go test ./... && go vet ./....

Repo Notes

  • .sophia/ is local-first workflow state and is ignored by Git by default.
  • _docs/ is local/internal and ignored via .gitignore.
  • If metadata drifts from Git history, run sophia repair.

Skills

  • Use $sophia for Sophia CLI workflow tasks.
  • Use other installed skills only when the task clearly matches them; the runtime skill registry is the source of truth.

Read the full file on GitHub · 55 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. 6d ago First seen · 55 lines · 514 tokens per session scan A 4655f133e4d5

Subscribe to this mod's changes

sophia AGENTS.md is an instructions file published in the GitHub repository Kevandrew/sophia (20 stars, last pushed 6mo ago), licensed MIT. It adds 514 tokens to every session, about $0.0026 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.