retrospective

retrospective is a command for Claude Code from jwynia/context-networks. It costs 0 tokens per session (1,453 once invoked), scanned A, original, MIT.

A post-task review prompt that examines completed work and records useful decisions, discoveries, and documentation gaps in a context network.

In plain words
What is it for?
It helps review objectives, architectural choices, unexpected problems, assumptions, and updates needed in project documentation.
Why use it?
It helps preserve important reasoning and lessons that might otherwise be lost after a task ends.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/jwynia/context-networks/retrospective
Clone the repo
git clone --depth 1 https://github.com/jwynia/context-networks

Made for: Claude Code.

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 retrospective

README.md
[![agentmods](https://agentmods.dev/badge/commands/jwynia/context-networks/retrospective.svg)](https://agentmods.dev/commands/jwynia/context-networks/retrospective)
Your own site
<a href="https://agentmods.dev/commands/jwynia/context-networks/retrospective"><img src="https://agentmods.dev/badge/commands/jwynia/context-networks/retrospective.svg" alt="Measured on agentmods" height="20"></a>
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 1,453 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 5.1 $0.00000 $0.01453
Opus 5 $0.00000 $0.00727
Sonnet 5 $0.00000 $0.00291
Haiku 4.5 $0.00000 $0.00145

Measured 6d ago against content hash d8acc9f376f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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/commands/retrospective.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Network Retrospective Agent Prompt

Task Context

You are conducting a retrospective analysis after completing a task. Your goal is to identify what should be captured in the context network and what adjustments need to be made to existing documentation.

Critical Domain Boundary Reminder

Remember the distinction:

  • Context Network: Planning documents, architecture decisions, design discussions, implementation strategies
  • Project Artifacts: Source code, configuration files, public documentation, tests

Retrospective Analysis Process

Phase 1: Task Review

  1. Task Summary

    • What was the original task objective?
    • What was actually accomplished?
    • Were there any deviations from the original plan?
  2. Decision Inventory

    • What architectural or design decisions were made?
    • What trade-offs were considered?
    • What alternatives were rejected and why?
  3. Discovery Log

    • What unexpected challenges emerged?
    • What new patterns or approaches were discovered?
    • What assumptions proved incorrect?
    • What discovery records were created during this task?
    • What location insights should be preserved?

Phase 2: Context Network Gap Analysis

  1. Missing Documentation

    • Were there planning documents that would have helped but didn't exist?
    • What design decisions were made that aren't captured anywhere?
    • Are there new patterns that should be documented?
    • What discovery records would have saved time if they existed?
    • What location indexes were missing that caused repeated file searching?
  2. Outdated Information

    • Did you encounter documentation that was incorrect or misleading?
    • Are there nodes whose relationships have changed?
    • Has the confidence level of any information changed (Established → Evolving)?
  3. Relationship Gaps

    • Are there connections between nodes that weren't documented?
    • Did you discover new cross-domain relationships?
    • Are there navigation paths that would have been helpful?

Read the full file on GitHub · 214 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. 6d ago First seen · 214 lines · 0 tokens per session scan A d8acc9f376f4

Subscribe to this mod's changes

retrospective is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,453 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 2026-08-30.