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/parkerm2/create-claude-workflow/retro-prepgit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWhat 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 | $0.00015 | $0.02517 |
| Opus 5 | $0.00008 | $0.01259 |
| Sonnet 5 | $0.00003 | $0.00503 |
| Haiku 4.5 | $0.00002 | $0.00252 |
Grade A, and why
retro-prep 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.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Retrospective Preparation
Automates collection of sprint metrics, trend analysis, and qualitative signals to prepare a comprehensive, data-driven retrospective document. Pulls velocity trends, PR metrics, bug data, blockers, and team sentiment signals.
Usage
/retro-prep [--sprint <sprint-id>] [--publish] [--raw]
--sprint <id>: Specify sprint ID (auto-detects last completed sprint if omitted)--publish: Save formatted retro doc to Confluence--raw: Output raw JSON data instead of formatted document
Workflow
Phase 1: Sprint Selection
Identifies the most recently completed sprint or uses the specified sprint ID.
// Pseudo-implementation
const sprints = await jira.getSprintsFromBoard({
boardId: detectBoardId(),
state: "closed"
});
const targetSprint = sprints[0]; // Most recent
if (!targetSprint) {
console.error("ERROR: No closed sprints found");
return gracefulFailure("No completed sprints available");
}
console.log(`✓ Sprint: ${targetSprint.name} (${targetSprint.id})`);
Graceful degradation: If no sprints found, prompt user for board selection or exit cleanly.
Phase 2: Metrics Collection
Fetches quantitative sprint data: story points, ticket counts, cycle times, bug rates.
const sprintTickets = await jira.getIssuesByJQL({
jql: `sprint = ${targetSprint.id}`
});
const metrics = {
committed: 0,
completed: 0,
carryover: 0,
completedPoints: 0,
committedPoints: 0,
bugsFiled: 0,
bugsFixed: 0,
avgCycleTime: 0,
prCount: 0,
avgMergeTime: 0,
ticketsByType: { Story: 0, Bug: 0, Task: 0, Subtask: 0 }
};
for (const ticket of sprintTickets) {
metrics.ticketsByType[ticket.issuetype.name]++;
if (ticket.status === "Done") {
metrics.completed++;
metrics.completedPoints += ticket.customfield_storypoints || 0;
} else {
metrics.carryover++;
}
metrics.committedPoints += ticket.customfield_storypoints || 0;
metrics.committed++;
// Calculate cycle time (created → done)
if (ticket.status === "Done") {
const created = new Date(ticket.created);
const resolved = new Date(ticket.resolutiondate);
const cycleHours = (resolved - created) / (1000 * 60 * 60);
metrics.avgCycleTime += cycleHours;
}
// Count bugs
if (ticket.issuetype.name === "Bug") {
if (ticket.status === "Done") metrics.bugsFixed++;
else metrics.bugsFiled++;
}
}
metrics.avgCycleTime = Math.round(metrics.avgCycleTime / metrics.completed);
metrics.completionRate = Math.round((metrics.completed / metrics.committed) * 100);
metrics.velocity = metrics.completedPoints;
console.log(`✓ Metrics collected: ${metrics.completed}/${metrics.committed} tickets, ${metrics.velocity}pt velocity`);
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.
- 3d ago First seen · 329 lines · 15 tokens per session scan A 3bf0fc855470
retro-prep is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 2,517 once invoked, about $0.0001 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.