implement-plan

A command guide for implementing the mcp-for-argo-workflows project from a plan stored in Linear, a project-management and issue-tracking service.

In plain words
What is it for?
It is for fetching Linear issues, finding unblocked setup, tool, testing, and documentation tasks, and presenting the work ready to implement.
Why use it?
It helps identify which tasks are ready by checking their status and dependencies before implementation begins.

Command for Claude Code

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 commands/pipekit/mcp-for-argo-workflows/implement-plan
Clone the repo
git clone --depth 1 https://github.com/pipekit/mcp-for-argo-workflows

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00624
Opus 5 $0.00000 $0.00312
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured yesterday against content hash fe289b4291da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-plan 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 yesterday.

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/commands/implement-plan.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan from Linear

You are orchestrating the implementation of the mcp-for-argo-workflows project based on the Linear project plan.

Step 1: Fetch Current State from Linear

First, retrieve the current project status:

  1. Use mcp__linear-server__list_issues with project: "mcp-for-argo-workflows" to get all issues
  2. Identify issues by status: Backlog, Todo, In Progress, Done
  3. Check issue dependencies (noted in each issue's description)

Step 2: Identify Ready Tasks

Analyze the issues to find tasks that are ready to implement:

  1. Setup tasks (PIP-5 through PIP-14) - Foundation work, check dependencies
  2. MCP tools (PIP-15 through PIP-49) - Require setup tasks complete
  3. Testing (PIP-50, PIP-51) - Require tools implemented
  4. Documentation (PIP-9, PIP-52, PIP-53) - Can be done incrementally

A task is "ready" when:

  • Status is Backlog or Todo
  • All dependencies (listed in issue description) are completed

Step 3: Present Ready Tasks

Present the list of ready tasks to the user with:

  • Issue identifier (e.g., PIP-10)
  • Title
  • Brief description of what it involves
  • Dependencies (and their status)

Step 4: Execute Implementation via /implement-issue

For each ready task, use the /implement-issue command to implement it:

/implement-issue PIP-XX

IMPORTANT: Always use /implement-issue to implement individual tasks. This ensures consistent implementation workflow across all tasks.

Wait for each task to complete before starting the next one.

Step 5: Report Progress

After each implementation cycle:

  1. Summarize what was completed
  2. List any blockers or issues encountered
  3. Identify next tasks ready for implementation (dependencies now met)
  4. Ask user if they want to continue with the next task

Implementation Guidelines

  • One task at a time - Complete and verify before moving to next
  • Always use /implement-issue - Never implement tasks directly in this command
  • Ask for clarification - If requirements are ambiguous, ask before implementing
  • Report blockers - If a task cannot be completed, report why and suggest alternatives

Read the full file on GitHub · 76 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. yesterday First seen · 76 lines · 0 tokens per session scan A fe289b4291da

Subscribe to this mod's changes

implement-plan is a command published in the GitHub repository pipekit/mcp-for-argo-workflows (5 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 624 tokens. 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.