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.
npx agentmods add commands/pipekit/mcp-for-argo-workflows/implement-issuegit clone --depth 1 https://github.com/pipekit/mcp-for-argo-workflowsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02466 |
| Opus 5 | $0.00000 | $0.01233 |
| Sonnet 5 | $0.00000 | $0.00493 |
| Haiku 4.5 | $0.00000 | $0.00247 |
Grade A, and why
implement-issue 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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Single Linear Issue
Implement a specific Linear issue for mcp-for-argo-workflows.
Usage
Provide the issue identifier (e.g., PIP-15) as an argument: /implement-issue PIP-15
The argument is: $ARGUMENTS
Step 1: Fetch Issue Details
- Use
mcp__linear-server__get_issuewith the provided issue ID - Parse the issue description for:
- Tasks/requirements
- Tool schema (if MCP tool)
- Implementation notes
- Dependencies
- Acceptance criteria
Step 2: Check Dependencies
- Identify dependencies from the issue description (usually listed at bottom)
- Verify each dependency is complete:
- Check Linear status
- Verify code exists locally
- If dependencies not met, report and stop
Step 3: Create Feature Branch
Create a branch for this issue using the Linear-suggested branch name:
git checkout main
git pull origin main
git checkout -b <branch-name-from-linear>
The branch name is provided in the Linear issue details as gitBranchName (e.g., alan/pip-10-implement-mcp-server-skeleton).
Step 4: Update Linear Status
Move issue to "In Progress":
mcp__linear-server__update_issue(id: "<issue-id>", state: "In Progress")
Step 5: Plan Agent Collaboration
Based on issue labels and content, determine which agents need to be involved:
Primary Implementation Agent
| Label | Primary Agent |
|---|---|
setup |
go-developer or ci-devops |
mcp-tool |
mcp-tool-implementer |
testing |
testing |
docs |
docs-examples |
ci |
ci-devops |
Supporting Agents (as needed)
testing- Write or update tests for the implementationdocs-examples- Update README, CLAUDE.md, or add examplesgo-developer- Review Go code patterns and architecturekubernetes-argo- Review Argo/K8s integration code
Agent Collaboration Patterns
- Implementation + Testing: Primary agent implements, then
testingagent adds/updates tests - Implementation + Docs: Primary agent implements, then
docs-examplesupdates documentation - Implementation + Review: Primary agent implements, then another agent reviews for correctness
- Full Pipeline: Implement → Test → Document → Review
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.
- yesterday First seen · 313 lines · 0 tokens per session scan A ab3279207ce0
implement-issue is a command published in the GitHub repository pipekit/mcp-for-argo-workflows (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,466 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.