icm-spec AGENTS.md

icm-spec AGENTS.md is an instructions file for Codex, OpenCode from andyrids/icm-spec. It costs 830 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for an ICM specification plugin, where ICM is a staged method for organising software work. It explains the project’s context layers, workflows, review gates, and handoffs.

In plain words
What is it for?
Use it when working on the ICM plugin, its workspace structure, stage contracts, plans, specifications, or review workflow.
Why use it?
It tells the agent which project information to load and when, helping each stage follow its intended boundaries and approval process.

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/andyrids/icm-spec/agents-md
Clone the repo
git clone --depth 1 https://github.com/andyrids/icm-spec

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 icm-spec AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andyrids/icm-spec/agents-md.svg)](https://agentmods.dev/instructions/andyrids/icm-spec/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/andyrids/icm-spec/agents-md"><img src="https://agentmods.dev/badge/instructions/andyrids/icm-spec/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 830 This file is loaded in full into every session.
When invoked 830 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 $0.00830 $0.00830
Opus 5 $0.00415 $0.00415
Sonnet 5 $0.00166 $0.00166
Haiku 4.5 $0.00083 $0.00083

Measured 3d ago against content hash 2e91889f03e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

icm-spec 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 3d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

icm-spec plugin

This project contains a plugin for implementing spec-driven development alongside Interpretable Context Methodology (ICM).

ICM orchestrates agent workflows through workspaces with folder structure, markdown and scripts.

Workspaces use dedicated pipelines containing stages with a specific input, process and output. Conditional and unconditional review gates MUST be respected to allow human inspection and feedback loops.

Context hierarchy

Five layers. Layers 0 to 2 route; layers 3 and 4 carry content. Load a layer only when the work has reached it - reading ahead is how a stage acquires context it was designed not to have.

Layer Role Path immutable Budget
0 Global identity AGENTS.md false 900
1 Workspace routing CONTEXT.md false 300
2 Stage routing ICM/*/CONTEXT.md false 500
2 Stage contract ICM/*/stages/**/CONTEXT.md false 500
3 Reference material ICM/_config/reference-*.md, both READMEs true 2500
3 Reference material specs/**/*.md false -
4 Working artifact plans/*.md false -
4 Working artifact ICM/*/stages/**/output/*.md false -

Frontmatter

Every file above carries context-hierarchy, context-hierarchy-role and immutable as tabled, plus recommended-context-tokens where a target is given. Beyond those:

  • Budgets are a signal, not an enforced limit. A file that outgrows one is worth a look - it may have started doing another layer's job. Specs are unbudgeted - a spec is as long as the behaviour it declares.
  • Layer 3 carries tags: [keyword, ...]. immutable: true marks the factory configuration, amended deliberately, not in passing. Specs are not part of it: the pipeline exists to amend them, and stage 01 owns every change.
  • plans/*.md carries status - planned | in-progress | done | blocked | cancelled - plus the query fields depends, specs, authors, issues and pr, contracted in plans/README.md. Every coverage and ripple check reads them.
  • ICM/*/stages/**/output/*.md carries status: in-progress | in-review | done. It is ephemeral scratch, gitignored.

Read the full file on GitHub · 65 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. 3d ago First seen · 65 lines · 830 tokens per session scan A 2e91889f03e0

Subscribe to this mod's changes

icm-spec AGENTS.md is an instructions file published in the GitHub repository andyrids/icm-spec (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 830 tokens to every session, about $0.0042 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.