skilled-agent-harness_spec-driven-loops: Instructions file for Codex

AGENTS.md

skilled-agent-harness_spec-driven-loops AGENTS.md is an instructions file for Codex, OpenCode from MichelKerkmeester/skilled-agent-harness_spec-driven-loops. It costs 6,112 tokens per session, scanned A, original, MIT.

A set of repository instructions that defines how an AI coding assistant should route work, follow safety rules, document changes, and verify results.

In plain words
What is it for?
Use it to guide work across multiple repositories, enforce pre-execution checks, choose the right coding workflow, and require evidence before claiming completion.
Why use it?
It gives development tasks consistent rules and prevents the assistant from making unverified or poorly scoped changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; reads ~/.codex paths.

This is MichelKerkmeester/skilled-agent-harness_spec-driven-loops's own configuration. It tells Codex and OpenCode how to work on skilled-agent-harness_spec-driven-loops 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 skilled-agent-harness_spec-driven-loops configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MichelKerkmeester/skilled-agent-harness_spec-driven-loops. 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/MichelKerkmeester/skilled-agent-harness_spec-driven-loops/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

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 skilled-agent-harness_spec-driven-loops AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md/github.svg)](https://agentmods.dev/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md"><img src="https://agentmods.dev/badge/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skilled-agent-harness_spec-driven-loops AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md"><img src="https://agentmods.dev/badge/instructions/michelkerkmeester/skilled-agent-harness_spec-driven-loops/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,112 This file is loaded in full into every session.
When invoked 6,112 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 $0.06112 $0.06112
Opus 5.5 $0.02445 $0.02445
Sonnet 5.5 $0.01222 $0.01222
Haiku 4.5 $0.00611 $0.00611

Measured 5d ago against content hash b427a127693c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skilled-agent-harness_spec-driven-loops 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 5d 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 · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Assistant Framework (Universal Template)

Universal behavior framework shared across repositories. Anything belonging to one repository lives in that repository's root REPO RULES.md, loaded by Gate 5 (§2).


1. 🚨 CRITICAL RULES — HARD BLOCKERS

Where a rule file expands a clause here, REPO RULES.md's trigger table routes the load.

The Four Laws — HARD BLOCKERS (cannot be overridden)
  1. READ FIRST — Never edit a file without reading it first. Understand context before modifying.
  2. SCOPE LOCK — Only modify files explicitly in scope. NO "cleaning up" or "improving" adjacent code. Scope in spec.md is FROZEN.
  3. VERIFY — Syntax checks and tests MUST pass before claiming completion. NO blind commits.
  4. HALT — Stop immediately where the §2 Confidence Thresholds say to ask, if line numbers don't match, or if tests fail. A failing check may be repaired, but forward progress and completion stay blocked until the authoritative gate passes.

The Iron Law: NO completion claims without running stack-appropriate verification.

PLAN-WORKFLOW LOCK — HARD BLOCKER (cannot be overridden)

When an approved plan names a specific workflow, command, agent or skill (e.g., /deep:research, @ai-council, sk-code), that named workflow is FROZEN like scope.

Before substituting a manual or alternative approach:

  1. VERIFY, don't assume — READ the named workflow's contract (its SKILL.md or command doc) to test any friction you believe it has.
  2. FLAG deviations — If it genuinely blocks the task, STATE the deviation to the user ("plan says X, I propose Y because Z") and get approval before proceeding.
  3. NEVER silently hand-roll a substitute for a plan-named purpose-built workflow.
  4. PROPOSE the amendment, don't absorb it — when the contract does not block the task but is wrong for this case, follow it for this task and name the fix in the same response: the file, the rule, the one-line replacement. The adjacent case, a frozen scope you believe is wrong, is scope-discipline.md §5 and §6.

Read the full file on GitHub · 297 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. 5d ago Changed · +11 tokens per session b427a127693c
  2. 14d ago Changed · -4 tokens per session c9cf5d92f095
  3. 17d ago Changed · +1 lines · +128 tokens per session c4c5c8798b5b
  4. 19d ago Changed · +6 lines · +26 tokens per session 70dee7b846b3
  5. 20d ago Changed · +4 lines · -39 tokens per session 515f240c1d56
  6. 23d ago Changed · +17 tokens per session 2dc268fa77dd
  7. 26d ago Changed · +64 tokens per session 32a4ad2c62fa
  8. 29d ago Changed · +1 lines · +155 tokens per session 21bc017ae1b3
  9. 1mo ago Changed · +36 tokens per session 3b099bdba725
  10. 1mo ago First seen · 285 lines · 5,718 tokens per session scan A c13df9262fad

Subscribe to this mod's changes

skilled-agent-harness_spec-driven-loops AGENTS.md is an instructions file published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (38 stars, last pushed today), licensed MIT. It adds 6,112 tokens to every session, about $0.0244 per session on Opus 5.5. 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 2026-09-03.

Related

Other instructions, from other repositories

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 · 9,715 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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens