agentmods.dev

seshat AGENTS.md

Repository instructions for Seshat, an open-source Go runtime for AI agents. They describe its command-line, gRPC server, and Go SDK entry points, along with required build, test, formatting, and branching practices.

In plain words
What is it for?
Building, testing, formatting, linting, and contributing changes to the Seshat Go repository while respecting its package boundaries and branch strategy.
Why use it?
They make the project’s quality checks and branch structure explicit before code is changed. This helps prevent skipped tests, disabled checks, or changes in the wrong branch.

Instructions file for CodexOpenCode

4 2d ago A scan 1,425 tokens original Apache-2.0
View the source file KPO-Tech/seshat
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/kpo-tech/seshat/agents-md
Clone the repo
git clone --depth 1 https://github.com/KPO-Tech/seshat

Made for: Codex, OpenCode.

Per session 1,425 This file is loaded in full into every session.
When invoked 1,425 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 $0.01425 $0.01425
Opus 5 $0.00713 $0.00713
Sonnet 5 $0.00285 $0.00285
Haiku 4.5 $0.00143 $0.00143

Measured 2d ago against content hash bafff005c3f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seshat 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.

AGENTS.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions — Seshat

This file provides guidance for AI agents (Seshat, Claude Code, Codex, or similar) working on this repository. Read it before making any changes.

Project overview

seshat is an open-source Go AI agent runtime. It has no concept of users, organizations, or billing — those live in seshat-ai (a separate private repository). The engine exposes three entry points: cmd/cli (terminal), cmd/grpc (gRPC server), and pkg/sdk (Go SDK for embedding).

Build and test

Always run these before finishing:

go build ./...          # must pass — no exceptions
go vet ./...            # must pass — no exceptions
go test -race ./...     # must pass — fix failures, do not skip
golangci-lint run ./... # pass or explain why an existing violation is pre-existing
gofmt -w .              # always run after editing Go files

If go test fails, investigate and fix the root cause. Do not disable tests or add t.Skip() to work around failures.

Branching strategy

main        production-ready, tagged releases only
  └── dev   stable integration — all work lands here first via PR
        └── <type>/<slug>   one branch per issue
  • Always branch off dev.
  • Never commit or push directly to main.
  • Never commit or push directly to dev.
  • All work must land through a PR: <type>/* → dev, then dev → main.
  • PRs target dev. The only allowed PR into main is dev → main for final validation by maintainers.
  • Direct PRs from topic branches into main must be closed without merge.
  • The Gate CI check (Build + Test + Lint) must be green before any PR can merge.
  • Name branches <type>/<short-slug> where <type> is one of feat, fix, docs, refactor, test, chore, perf, or ci.

If an exceptional direct push ever lands on main, stop feature work and realign dev from main immediately before opening new feature branches.

Package boundary rules (critical)

  • pkg/ is the public API. Do not add internal/ types to pkg/ signatures without explicit need.
  • internal/ packages must never import pkg/ — dependency flows one way: entry points → pkg/sdk → internal/.
  • internal/backend does not exist here. It lives in seshat-ai. Do not recreate it.
  • New tools go in internal/tools/<category>/. Register them in internal/tools/builtin/builtin.go.
  • New providers go in internal/providers/. Add a wire-format adapter in internal/providers/adapter.go.

Read the full file on GitHub · 138 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. 2d ago First seen · 138 lines · 1,425 tokens per session scan A bafff005c3f8

Subscribe to this mod's changes

seshat AGENTS.md is an instructions file published in the GitHub repository KPO-Tech/seshat (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,425 tokens to every session, about $0.0071 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.

Data and AIGit and workflowLLMTestingagent-runtimeai-agentsclimcp
Related

Other instructions, from other repositories

Sponsio CLAUDE.md

Instructions for SponsioLabs/Sponsio, covering agent guide for sponsio, what sponsio is, positioning, what to read first and repository map.

SponsioLabs/Sponsio · 1,937 tokens

gini-agent AGENTS.md

AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.

Open-Curiosity/gini-agent · 3,639 tokens

DashClaw copilot-instructions.md

Instructions for ucsandman/DashClaw, covering dashclaw — github copilot instructions, design context, users, brand personality and aesthetic direction.

ucsandman/DashClaw · 1,691 tokens

deepseek-harness-handbook AGENTS.md

Instructions for sandbaseai/deepseek-harness-handbook, covering contributor instructions, product boundary, content workflow, safety and project handoff and promotion playbook.

sandbaseai/deepseek-harness-handbook · 1,999 tokens

pi AGENTS.md

Instructions for TGYD-helige/pi, covering pi extensions monorepo — agent guidelines, project overview, required agent skills, ponytail — minimal-code discipline and mattpocock/skills — engineering workflow skills.

TGYD-helige/pi · 4,423 tokens

OpenGameAgent AGENTS.md

Instructions for EricSun0218/OpenGameAgent, covering coding agent guide, objective, repository map, non-negotiable boundaries and first commands.

EricSun0218/OpenGameAgent · 1,042 tokens