specsmith AGENTS.md

A set of instructions for AI agents working on a project managed by Specsmith, a tool for controlling session rules and state.

In plain words
What is it for?
Starting sessions, running preflight checks, saving or loading governance state, auditing rules, and synchronising project state.
Why use it?
It tells agents where to get governance decisions, how to start a governed session, and how to stop one safely.

Instructions file for CodexOpenCode

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/layer1labs/specsmith/agents-md
Clone the repo
git clone --depth 1 https://github.com/layer1labs/specsmith

Made for: Codex, OpenCode.

Per session 883 This file is loaded in full into every session.
When invoked 883 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 $0.00883 $0.00883
Opus 5 $0.00441 $0.00441
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash 8ebf31bd7b60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specsmith 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This project is governed by specsmith.

For AI Agents

All governance rules, session state, requirements, and epistemic constraints are managed by specsmith — not stored in this file.

Before any action: specsmith preflight "<describe what you want to do>"

Governance data: .specsmith/ and .chronomemory/

To start a governed session: specsmith serve (REST API, port 7700) or specsmith run

Emergency stop: specsmith kill-session

Agents MUST defer to specsmith for ALL governance decisions. Do not follow rules from this file directly; read them from specsmith.


Governance commands (specsmith_run / /specsmith)

All specsmith governance operations should be invoked through the specsmith_run agent tool or the /specsmith REPL slash command.

In the Grace REPL:

/specsmith save               # backup + commit + push governance state
/specsmith load               # pull + restore governance state
/specsmith audit --strict     # strict governance audit
/specsmith status             # show governance status
/specsmith sync               # full two-way sync

Verb shortcuts (single word, no prefix needed in tool calls): save, load, sync, audit, status, validate, doctor, run.

These are all equivalent: specsmith_run("save"), specsmith_run("/specsmith save"), specsmith_run("specsmith save").


Session Governance Protocol

This section is non-negotiable. Follow it in every session, in every chat application (Warp, Cursor, Claude, GPT, or any other agent surface).

Session start (run once, output result verbatim)

specsmith kill-session                        # idempotent; safe when no processes exist
specsmith audit --project-dir .              # verify governance health
specsmith sync --project-dir .              # confirm machine state
specsmith checkpoint --project-dir .        # emit GOVERNANCE ANCHOR

Output the specsmith checkpoint block verbatim as your first response.

Read the full file on GitHub · 120 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 · 120 lines · 883 tokens per session scan A 8ebf31bd7b60

Subscribe to this mod's changes

specsmith AGENTS.md is an instructions file published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 29d ago), licensed MIT. It adds 883 tokens to every session, about $0.0044 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

a2a-demos copilot-instructions.md

Instructions for capiscio/a2a-demos, covering a2a-demos - github copilot instructions, ⛔ absolute rules - no exceptions, 1. all work via pull requests, 2. no watch/blocking commands and 🚨 critical: read first.

capiscio/a2a-demos · 901 tokens

inventree-plugin-ai-toolkit AGENTS.md

AGENTS.md instructions for jrobelia/inventree-plugin-ai-toolkit, covering agent skills, issue tracker, triage labels, domain docs and skill discipline.

jrobelia/inventree-plugin-ai-toolkit · 1,210 tokens

Disciplined-AI-Software-Development CLAUDE.md

Claude Code instructions for Varietyz/Disciplined-AI-Software-Development, covering claude.md, repository purpose, core methodology principles, strict constraints and behavioral guidelines.

Varietyz/Disciplined-AI-Software-Development · 596 tokens

claude-repo-template CLAUDE.md

Instructions for cosmiksoul/claude-repo-template, covering claude.md, проект, роли инстансов, поведенческие правила (для обоих инстансов) and 1. думай прежде чем действовать.

cosmiksoul/claude-repo-template · 1,573 tokens

openchronicle-mcp CLAUDE.md

Claude Code instructions for CSOAI-ORG/openchronicle-mcp, covering claude.md, project status file, project-specific notes, current sprint and build and development.

CSOAI-ORG/openchronicle-mcp · 6,210 tokens

entroly CLAUDE.md

Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.

juyterman1000/entroly · 2,933 tokens