agentmods.dev

mac-shell-mcp CLAUDE.md

mac-shell-mcp CLAUDE.md is an instructions file for coding agents from cfdude/mac-shell-mcp. It costs 4,168 tokens per session, scanned A, original, MIT.

Repository instructions for an AI coding agent working with a project-management workflow called PM Conductor. They define how work is split into epics and how blocked tasks are handled.

In plain words
What is it for?
Managing epics and smaller stories, recording minor or substantial detours, resuming interrupted work, and checking project status.
Why use it?
They keep task progress, detours, priorities, and review decisions recorded consistently instead of relying on hand-edited project notes.

Instructions file

not rated 24 5d ago A scan 4,168 tokens original MIT
View the source file cfdude/mac-shell-mcp
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/cfdude/mac-shell-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/cfdude/mac-shell-mcp

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 mac-shell-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cfdude/mac-shell-mcp/claude-md.svg)](https://agentmods.dev/instructions/cfdude/mac-shell-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cfdude/mac-shell-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cfdude/mac-shell-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,168 This file is loaded in full into every session.
When invoked 4,168 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 $0.04168 $0.04168
Opus 5 $0.02084 $0.02084
Sonnet 5 $0.00834 $0.00834
Haiku 4.5 $0.00417 $0.00417

Measured 4d ago against content hash 5e5174933ec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mac-shell-mcp CLAUDE.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 4d 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.

CLAUDE.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

PM Conductor — operating rules

This repo is managed by the pm plugin. The conductor sits ABOVE OpenSpec and Superpowers. Epics are lane-agnostic (openspec | superpowers | claude-code | decision | external); OpenSpec is one lane. Stories come from each epic's source (OpenSpec tasks.md, a Superpowers plan, or a manual list). Follow these rules:

  1. Detours — when something blocks the active epic, CLASSIFY before fixing:
    • Minimal (small, self-contained, no design ambiguity): fix → test → commit → push, then run /pm:detour --minimal "<what>" so it is recorded in .conductor/detours.log. Then resume.
    • Substantial (own design / changes shared behavior / multi-step): run /pm:detour. It becomes its own epic in the appropriate lane (OpenSpec proposal, Superpowers plan, etc.); PUSH the current epic onto the detour stack in .conductor/state.json with a concrete reason and reconcileOnResume.
  2. State of record is .conductor/state.json. After any change to epics, status, priority, or the detour stack, re-render with /pm:status. Never hand-edit PROJECT.md.
  3. Resuming after a detour — use /pm:resume. If the popped frame had reconcileOnResume, run the reconcile gate (reconciler agent) BEFORE writing code, then write its verdict back durably with record-reconcile <id> --detour <id> --verdict valid|invalidated [--amendments "<a>;<b>"] — this attaches {verdict, amendments, reconciledAt} to the paused epic's link to the detour and clears reconcileNeeded, instead of the judgment only ever living in conversation.
  4. Honcho — on every PUSH and POP, also write a one-line memory to Honcho ("paused X for Y" / "resumed X, reconciled vs Y") so the relationship survives outside this repo.
  5. Keep tasks.md checkboxes truthful — they are the source of truth for story progress.
  6. Roadmap as backlog — work you intend to do but haven't proposed yet can be registered now with /pm:epic add … --status planned (any lane). Planned epics show as ordered backlog in PROJECT.md and a planned: N count in the briefing, without a "no change on disk" warning; /pm:sync flips an openspec planned epic to untriaged once its change is proposed. Have a roadmap doc? Read it in-session and load each item this way.

Read the full file on GitHub · 238 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. 4d ago First seen · 238 lines · 4,168 tokens per session scan A 5e5174933ec4

Subscribe to this mod's changes

mac-shell-mcp CLAUDE.md is an instructions file published in the GitHub repository cfdude/mac-shell-mcp (24 stars, last pushed 5d ago), licensed MIT. It adds 4,168 tokens to every session, about $0.0208 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.

Project managementmacmcpzsh
Related

Other instructions, from other repositories

ESAA-Core AGENTS.md

Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.

elzobrito/ESAA-Core · 2,154 tokens

Kanvas AGENTS.md

Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.

XMihura/Kanvas · 1,009 tokens

delivery-loop CLAUDE.md

Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.

blakemartz/delivery-loop · 2,076 tokens

taskcenter AGENTS.md

AGENTS.md instructions for xiaogezi/taskcenter, covering taskcenter agent rules, safety boundaries, required workflow and verification.

xiaogezi/taskcenter · 248 tokens

idd-skill idd-resume.instructions.md

Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.

kurone-kito/idd-skill · 3,747 tokens

codecrucible AGENTS.md

Instructions for block/codecrucible, covering agent instructions, quick reference and landing the plane (session completion).

block/codecrucible · 333 tokens