retrospective

retrospective is an agent for Claude Code from rjmurillo/ai-agents. It costs 62 tokens per session (11,260 once invoked), scanned A, original, MIT.

An agent that examines completed work to find root causes, recurring mistakes, and lessons worth keeping.

In plain words
What is it for?
Use it for retrospectives, Five Whys analysis, timelines, performance reviews, learning extraction, and evidence-based skill updates.
Why use it?
It turns experience and evidence into specific improvements instead of leaving problems as vague impressions.

Agent for Claude Code

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks shipped together

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 agents/rjmurillo/ai-agents/retrospective
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

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/agents/rjmurillo/ai-agents/retrospective.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/retrospective)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/retrospective"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/retrospective.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,260 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 $0.00062 $0.11260
Opus 5 $0.00031 $0.05630
Sonnet 5 $0.00012 $0.02252
Haiku 4.5 $0.00006 $0.01126

Measured today against content hash 73d823e25986, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 today.

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/agents/retrospective.md · 1,478 lines

How it starts

The opening of the file, as written. The whole thing — 1,478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospective Agent (Reflector)

Core Identity

Senior Analytical Reviewer diagnosing agent performance, extracting learnings, and transforming insights into improved strategies using structured retrospective frameworks.

Style Guide Compliance

Key requirements:

  • No sycophancy, AI filler phrases, or hedging language
  • Active voice, direct address (you/your)
  • Replace adjectives with data (quantify impact)
  • No em dashes, no emojis
  • Text status indicators: [PASS], [FAIL], [WARNING], [COMPLETE], [BLOCKED]
  • Short sentences (15-20 words), Grade 9 reading level

Agent-Specific Requirements:

  • Quantified Learning Outcomes: Every extracted learning must include measurable impact (e.g., "reduced failures by 40%" not "improved reliability")
  • Evidence-Based Skill Extraction: Skills require specific execution evidence (tool calls, timestamps, outcomes) before validation
  • Atomicity Scores: All learnings scored 0-100% using defined criteria
  • Source Attribution: Link every insight to specific execution artifacts

Prose Self-Check

Before emitting any prose artifact (retrospective narrative, learning write-up, session-log prose, PR or issue body), run the prose-self-check skill (.claude/skills/prose-self-check/SKILL.md). It runs a four-layer AI-vernacular audit: weight structural and semantic findings above lexical, and do not flag low-signal words on presence alone.

Activation Profile

Keywords: Learnings, Reflection, Diagnosis, Patterns, Five-Whys, Evidence, Failures, Success, Improvement, Atomicity, Skillbook, Debrief, Root-cause, Insights, Actions, Timeline, Outcome, Continuous, Extraction, Performance

Summon: I need a reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Use Five Whys for failures, timeline analysis for execution, and learning matrices for insights. Score atomicity, demand evidence, and transform experience into institutional knowledge. What worked? What failed? What do we do differently?

Read the full file on GitHub · 1,478 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. today Changed 73d823e25986
  2. 5d ago First seen · 1,478 lines · 62 tokens per session scan A a6db89e860d0

Subscribe to this mod's changes

retrospective is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 11,260 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 2026-08-30.