speclock AGENTS.md

Development instructions for SpecLock, a Node.js tool that checks planned actions against rules and can connect to coding tools through MCP, a shared tool interface.

In plain words
What is it for?
Checking planned changes, running tests, updating versions, handling hook input safely, and keeping support for Claude Code, Cursor, Windsurf, Cline, Codex, and other MCP clients.
Why use it?
They help maintain the tool's safety rules, compatibility, tests, versions, and public command interfaces while preventing unauthorized releases or data leaks.

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/sgroy10/speclock/agents-md
Clone the repo
git clone --depth 1 https://github.com/sgroy10/speclock

Made for: Codex, OpenCode.

Per session 262 This file is loaded in full into every session.
When invoked 262 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 $0.00262 $0.00262
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 70d32b65ef3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speclock 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 · 32 lines

What it actually says

SpecLock Development Guide

Project

SpecLock is an MIT-licensed Node.js AI constraint engine. Keep changes focused, preserve the public CLI and MCP APIs, and do not weaken enforcement behavior.

Required checks

  • Run npx speclock check "<planned action>" before changing code.
  • Run npm test before proposing a release.
  • Changes under src/ require a version bump in every location documented in CLAUDE.md. Documentation, metadata, tests, and plugin packaging do not.
  • Never publish, deploy, tag, push, or create a pull request without explicit maintainer approval.

Security

  • Do not commit credentials, deployment identifiers, customer data, or rules copied from another project.
  • Claude Code hook handlers must parse JSON from stdin, cap untrusted input sizes, and fail open on internal errors.
  • Hard enforcement may deny an action only when SpecLock itself reports a blocked conflict. Advisory conflicts must remain warnings.

Compatibility

  • Node.js 18 and later are supported.
  • Keep the local stdio MCP server compatible with Claude Code, Cursor, Windsurf, Cline, Codex, and other MCP clients.
  • Use current official Claude Code plugin and hook schemas.
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 · 32 lines · 262 tokens per session scan A 70d32b65ef3d

Subscribe to this mod's changes

speclock AGENTS.md is an instructions file published in the GitHub repository sgroy10/speclock (25 stars, last pushed 15d ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 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.