agentmods.dev

session-retrospective-miner

session-retrospective-miner is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 34 tokens per session (2,365 once invoked), scanned A, original, MIT.

A reporting tool that reads coding-agent session logs and calculates how efficiently sessions used tools and retries. It produces a structured retrospective with recommendations for improving future prompts, plans, and project instructions.

In plain words
What is it for?
Use it to review Claude or EVOKORE sessions, measure tool usage and retry rates, and create improvement recommendations for workflows and instruction files.
Why use it?
It removes the need to collect session data and identify recurring problems by hand. Teams can see where agent work wastes time and what to change next.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md.

not rated 3repo 3mo ago A scan 34 tokens original MIT

Good fit Use it to review Claude or EVOKORE sessions, measure tool usage and retry rates, and create improvement recommendations for workflows and instruction files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmre/evokore-mcp-public/session-retrospective-miner
View source ↗ mattmre/EVOKORE-MCP-PUBLIC
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 mattmre/EVOKORE-MCP-PUBLIC --skill session-retrospective-miner
Clone the repo
git clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLIC

Made for: Claude Code, Codex.

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 session-retrospective-miner

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/session-retrospective-miner/github.svg)](https://agentmods.dev/skills/mattmre/evokore-mcp-public/session-retrospective-miner)
Your own site
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/session-retrospective-miner"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/session-retrospective-miner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for session-retrospective-miner

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/session-retrospective-miner"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/session-retrospective-miner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,365 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 $0.00034 $0.02365
Opus 5 $0.00017 $0.01182
Sonnet 5 $0.00007 $0.00473
Haiku 4.5 $0.00003 $0.00236

Measured 8d ago against content hash 142904f0a34a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

session-retrospective-miner 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 8d 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.

SKILLS/ORCHESTRATION FRAMEWORK/session-retrospective-miner/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Retrospective Miner

Purpose

A data-driven retrospective skill that automatically mines session data across all repos and produces actionable narrative improvement recommendations. The backward-looking complement to ARCH-AEP: AEP plans and executes forward; this skill looks back and improves the inputs for the next cycle.

This skill automates Phase 1 (Metrics Collection) of the improvement-cycles skill — no manual data gathering required.

Session Data ──► Retrospective Miner ──► Narrative Quality Score
                                               │
                                               ▼
                               Specific improvement recommendations
                                               │
                                               ▼
                       Updated phase specs, CLAUDE.md, prompt templates
                                               │
                                               ▼
                               Next cycle's AEP Align phase (better inputs)

Prerequisites

This skill uses two MCP tools from EVOKORE-MCP that must be available:

  • session_analyze_replay — aggregates tool frequency, retry rates, and hook events across session replay logs
  • session_work_ratio — computes useful-work density (evidence entries / replay entries) per session

Both tools were added in EVOKORE-MCP v3.1. Verify with discover_tools before running.

Input Parameters

time_window: "last-7-days" | "last-30-days" | "this-week" | "all-time"
project_filter: "all" | "Claudius-Maximus" | "OCR_LOCAL" | "EDCTool" | "<any slug>"
focus: "narrative-quality" | "tool-efficiency" | "phase-implementation" | "all"
min_session_turns: 10   # exclude trivial/exploratory sessions (default: 10)

Execution Steps

Step 1: Locate session files

Scan ~/.claude/projects/ for project slugs matching project_filter. For each matching slug:

  • List all .jsonl files in ~/.claude/projects/<slug>/
  • Filter by modification time to match time_window
  • Skip files with fewer than min_session_turns entries (count lines / ~4 entries per turn)

Read the full file on GitHub · 276 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. 8d ago First seen · 276 lines · 34 tokens per session scan A 142904f0a34a

Subscribe to this mod's changes

session-retrospective-miner is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,365 once invoked, about $0.0002 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 2026-09-03.

Analytics and metricsBuilding agentsagentic-aiaggregatorai-toolsclaudecontinuous-improvementefficiencyhitlmetricsnarrative-qualityorchestration-frameworkretrospectivesession-analysis
Related

Other skills, from other repositories

analytics-product

Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.

LiHongwei-cn/lihongwei-cn · 35 tokens

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.

LiHongwei-cn/lihongwei-cn · 34 tokens

law-of-similarity

Apply the Law of Similarity — shared colour, shape, or size signals that elements belong to one category. Use when signalling relationships across distance. For grouping by position, use law-of-proximity.

Owl-Listener/designer-skills · 47 tokens

law-of-common-region

Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.

Owl-Listener/designer-skills · 48 tokens

version-control-strategy

Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).

Owl-Listener/designer-skills · 50 tokens

presentation-deck

Structure a design presentation for a specific audience and decision. Use when presenting internally. For a portfolio narrative use case-study; for the written argument use design-rationale.

Owl-Listener/designer-skills · 39 tokens