capacities-mcp: Instructions file for Codex

AGENTS.md

capacities-mcp AGENTS.md is an instructions file for Codex, OpenCode from Im-Hal-9K/capacities-mcp. It costs 1,087 tokens per session, scanned A, original, from a forked repository, MIT.

A set of project instructions for the capacities-mcp codebase. It includes required practices for JavaScript, SQL, and TypeScript.

In plain words
What is it for?
Developing or reviewing JavaScript, SQL, and TypeScript changes in the Im-Hal-9K/capacities-mcp project.
Why use it?
It gives contributors one source of rules for writing and reviewing code consistently.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Im-Hal-9K/capacities-mcp's own configuration. It tells Codex and OpenCode how to work on capacities-mcp 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 capacities-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Im-Hal-9K/capacities-mcp. 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/Im-Hal-9K/capacities-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Im-Hal-9K/capacities-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 capacities-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/im-hal-9k/capacities-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/im-hal-9k/capacities-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/im-hal-9k/capacities-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/im-hal-9k/capacities-mcp/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 capacities-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/im-hal-9k/capacities-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/im-hal-9k/capacities-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,087 This file is loaded in full into every session.
When invoked 1,087 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 fork From a forked repository.
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 $0.01087 $0.01087
Opus 5.5 $0.00435 $0.00435
Sonnet 5.5 $0.00217 $0.00217
Haiku 4.5 $0.00109 $0.00109

Measured 1mo ago against content hash 53812f8cea9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capacities-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 1mo 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Packmind Standards

Before starting your work, make sure to review the coding standards relevant to your current task.

Always consult the sections that apply to the technology, framework, or type of contribution you are working on.

All rules and guidelines defined in these standards are mandatory and must be followed consistently.

Failure to follow these standards may lead to inconsistencies, errors, or rework. Treat them as the source of truth for how code should be written, structured, and maintained.

Standard: JavaScript Best Practices

This standard covers high-impact JavaScript patterns for robustness and safety: reliable async control flow, error propagation, resource cleanup, input validation, network timeouts and retries, config... :

  • Avoid async callbacks in Array.forEach/map without awaiting; use for...of for sequencing or Promise.all with explicit concurrency limits.
  • Avoid eval, Function, and dynamic import paths from untrusted data; use explicit dispatch maps for extensibility.
  • Centralize configuration loading and freeze the exported config object; disallow runtime mutation and avoid reading process.env throughout the codebase.
  • Guard shared mutable state across async boundaries with explicit ownership, atomics, or a single-writer queue; avoid read-modify-write on shared objects.
  • Propagate errors with original cause using Error options or rethrow; avoid catch blocks that only log or return defaults.
  • Release resources deterministically by awaiting stream completion and closing handles in finally; use pipeline/using patterns where available.
  • Retry only idempotent operations with bounded attempts, exponential backoff, and jitter; surface the final error without wrapping away the cause.
  • Set explicit timeouts and cancellation for every network or IPC request using AbortController and per-request deadlines.
  • Use structured logging with stable keys and redaction; avoid logging secrets or whole objects containing credentials.
  • Validate and normalize untrusted input at module boundaries using allowlists and type checks; reject extra fields and unexpected encodings.

Read the full file on GitHub · 59 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. 1mo ago First seen · 59 lines · 1,087 tokens per session scan A 53812f8cea9c

Subscribe to this mod's changes

capacities-mcp AGENTS.md is an instructions file published in the GitHub repository Im-Hal-9K/capacities-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,087 tokens to every session, about $0.0043 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories