ipe-mcp AGENTS.md

ipe-mcp AGENTS.md is an instructions file for Codex, OpenCode from Mik1810/ipe-mcp. It costs 1,494 tokens per session, scanned A, original, MIT.

Repository instructions for working on the ipe-mcp project. They define the required source of truth, workflow, and rule that one agent owns repository work from inspection through verification.

In plain words
What is it for?
They are for guiding repository tasks on ipe-mcp, including inspection, planning, implementation, targeted verification, and self-review.
Why use it?
They give an agent explicit operating rules, reducing uncertainty about how to plan, implement, review, and verify changes in that repository.

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/mik1810/ipe-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Mik1810/ipe-mcp

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 ipe-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mik1810/ipe-mcp/agents-md.svg)](https://agentmods.dev/instructions/mik1810/ipe-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mik1810/ipe-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mik1810/ipe-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,494 This file is loaded in full into every session.
When invoked 1,494 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 $0.01494 $0.01494
Opus 5 $0.00747 $0.00747
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00149 $0.00149

Measured 3d ago against content hash e87978fb9ae5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ipe-mcp 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Operating Rules

These rules apply to repository work.

Primary objective

Complete the requested task correctly with one agent, bounded context, and as few model/tool round trips as practical.

The same agent owns the task end-to-end: inspection, implementation, self-review, correction, verification, and final report.

1. Mono-agent rule

  • Do not spawn, delegate to, or coordinate subagents for repository work.
  • Do not split one task into implementer/reviewer/corrector/verifier/gate roles.
  • Perform review and verification as bounded phases of the same task.
  • Do not create worker handoffs, candidate digests, role payloads, or milestone state files unless the user explicitly asks for them.

2. Source of truth

Use, in order:

  1. the user's request and acceptance criteria;
  2. the referenced GitHub issue/milestone, when applicable;
  3. repository documentation and ADRs;
  4. the current Git state and relevant code/tests.

Do not reconstruct history that is already represented by Git or repository documentation.

3. Default workflow

Use the finite workflow described in .agents/WORKFLOW.md:

INSPECT
  -> PLAN
  -> IMPLEMENT
  -> TARGETED VERIFY
  -> ONE SELF-REVIEW
  -> CORRECT IF NEEDED
  -> FINAL VERIFY
  -> REPORT

Do not add extra phases merely to increase confidence after the acceptance criteria are satisfied.

3.1 MCP agentic-harness compliance

Apply .agents/MCP_HARNESS_COMPLIANCE.md whenever changed paths or behavior touch the MCP server, model-facing contract, host integration, permissions/write safety, transport/privacy, or their gates.

  • During planning, record mcp_harness_compliance.applicable_areas, evidence_required, and either proportional evidence needs or a concrete not_applicable_reason.
  • During the one self-review, reclassify against the actual diff and record evidence/findings for every applicable area.
  • During final verification and reporting, name the applicable areas and the concrete checks that passed. Run the complete six-area audit only for a cross-cutting MCP milestone or an explicit audit request.
  • Do not create task, review, handoff, or gate state files solely to satisfy this rule. If the user explicitly requests such an artifact, it must carry the policy's structured schema.

Read the full file on GitHub · 196 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 · 196 lines · 1,494 tokens per session scan A e87978fb9ae5

Subscribe to this mod's changes

ipe-mcp AGENTS.md is an instructions file published in the GitHub repository Mik1810/ipe-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 1,494 tokens to every session, about $0.0075 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

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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 · 7,296 tokens