parallel-retrospective

parallel-retrospective is a skill for Claude Code from jimmc414/claude-code-plugin-marketplace. It costs 69 tokens per session (4,620 once invoked), scanned A, original, MIT.

A read-only review tool for completed workflows where several workers handled tasks in parallel.

In plain words
What is it for?
Use it for retrospectives, post-mortems, workflow quality reviews, planning assessments, and recommendations for future parallel work.
Why use it?
It turns git history and task records into evidence-based lessons, so teams can find recurring process problems instead of relying on memory.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; positional $N argument.

Part of the parallel-workflows plugin — 3 skills, 3 agents shipped together

Good fit Use it for retrospectives, post-mortems, workflow quality reviews, planning assessments, and recommendations for future parallel work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jimmc414/claude-code-plugin-marketplace/parallel-retrospective
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.

Any agent
npx skills add jimmc414/claude-code-plugin-marketplace --skill parallel-retrospective
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Made for: Claude Code.

Or install parallel-workflows, the plugin that ships this one along with the rest of its 3 skills, 3 agents.

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 parallel-retrospective

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/parallel-retrospective.svg)](https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/parallel-retrospective)
Your own site
<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/parallel-retrospective"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/parallel-retrospective.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00069 $0.04620
Opus 5 $0.00034 $0.02310
Sonnet 5 $0.00014 $0.00924
Haiku 4.5 $0.00007 $0.00462

Measured 4d ago against content hash effaa20793a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

parallel-retrospective 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.

plugins/parallel-workflows/skills/parallel-retrospective/SKILL.md · 653 lines

How it starts

The opening of the file, as written. The whole thing — 653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Workflow Retrospective

You are a workflow analyst reviewing completed (or failed) parallel workflow sessions. Your role is to analyze git history, identify what worked and what didn't, and produce actionable recommendations. You operate in read-only mode—you never modify branches or commits.

Core Principles

  1. Evidence-based: Every finding cites specific commits
  2. Actionable: Recommendations are concrete, not vague
  3. Systemic focus: Distinguish one-off mistakes from patterns worth fixing
  4. Read-only: You analyze but never modify

Inputs Required

Before starting analysis, gather:

Required

  • Worker branches: All work/task-<id>-<description> branches from the workflow
  • Integration branch: The integration/<feature> branch (if workflow completed)
  • Original task description: What the orchestrator was asked to accomplish

Optional

  • User notes: Any issues encountered that aren't visible in git
  • Orchestrator's original split: The proposed workstream division
  • Work Item Manifest: The Phase 0 output showing extracted items, complexity estimates, groupings, and assumptions (enables Planning Quality Assessment)

Conventions Reference

This skill analyzes workflows created by the parallel-orchestrator and parallel-worker skills. You must understand their conventions:

Commit Prefix Conventions

Prefix Meaning What to Analyze
[CHECKPOINT] Subtask complete, work continuing Frequency, timing gaps, granularity
[BLOCKED:<reason>] Worker cannot proceed Reason patterns, resolution time, frequency
[NEEDS:task-X/<item>] Cross-dependency on another worker Avoidability, resolution, planning gaps
[COMPLETE] All assigned work finished Presence, summary quality, timing

Naming Conventions

Item Expected Pattern
Worktree directory worktrees/task-<id>-<description>/
Worker branch work/task-<id>-<description>
Integration branch integration/<feature>

Read the full file on GitHub · 653 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 · 653 lines · 69 tokens per session scan A effaa20793a9

Subscribe to this mod's changes

parallel-retrospective is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 4,620 once invoked, about $0.0003 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 2026-09-04.

Related

Other skills, from other repositories

audit-progressive-disclosure

Read-only progressive-disclosure audit for agent-facing instruction markdown. Grades every target against a three-tier load-cost model (always-loaded / invocation-loaded / on-demand) and classifies seven finding shapes in two lanes: split opportunities (oversize vs tier-calibrated Anthropic-prescribed caps…

melodic-software/claude-code-plugins · 259 tokens

quiz-me

Post-work comprehension check: after a change is complete, generate a self-contained HTML report of what was done (context, intuition, decisions) with a quiz at the bottom that you answer. Verifying the HUMAN absorbed the work, not the artifact. Non-gating by default; the quizpolicy userConfig tunes offer cadence.…

melodic-software/claude-code-plugins · 177 tokens

shape

Shape the assistant's output for a reader with ADHD, and anyone who wants action-first, low-friction responses. Lead with the concrete next action, number multi-step work, restate state across turns, cap and rank lists, give concrete time estimates, make wins visible, and cut preamble, recap, and closers. Use when…

melodic-software/claude-code-plugins · 209 tokens

generate

Build a source-backed AI industry briefing from official vendor publications, configured RSS feeds, GitHub releases, reputable secondary reporting, and user-supplied URLs. Use when: 'ai briefing', 'ai news', 'what's new in AI', 'catch me up on AI', 'prep for AI meeting', 'AI roundup', or 'generate AI slides'.

melodic-software/claude-code-plugins · 72 tokens

changelog

Ingest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis, no edits), status (applied versions), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC…

melodic-software/claude-code-plugins · 84 tokens

audit-comment-residue

Classify code comments for four residue shapes. History narration ("used to… now…"), plan/session references ("Task 2 replaces the old…", "in this PR"), conversational antecedents ("per your request", "as you asked"), and ticket/PR/branch back-references a future reader will never see. Emitting Tier 1 (remove) and…

melodic-software/claude-code-plugins · 159 tokens