improvement-cycles

improvement-cycles is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 14 tokens per session (1,358 once invoked), scanned A, original, MIT.

A repeatable process for reviewing coding-agent work, finding patterns in its results, and applying improvements in later cycles. It combines measurements, retrospectives, and tracking of whether changes were adopted.

In plain words
What is it for?
Use it to collect session metrics, review successes and failures, create improvement actions, and update prompts, phase specifications, or project instructions.
Why use it?
It removes the need to treat every agent session as a one-off experiment. Teams can compare outcomes over time and turn recurring problems into concrete process changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to collect session metrics, review successes and failures, create improvement actions, and update prompts, phase specifications, or project instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmre/evokore-mcp-public/improvement-cycles
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 improvement-cycles
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 improvement-cycles

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/improvement-cycles/github.svg)](https://agentmods.dev/skills/mattmre/evokore-mcp-public/improvement-cycles)
Your own site
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/improvement-cycles"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/improvement-cycles/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 improvement-cycles

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/improvement-cycles"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/improvement-cycles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,358 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 $0.00014 $0.01358
Opus 5 $0.00007 $0.00679
Sonnet 5 $0.00003 $0.00272
Haiku 4.5 $0.00001 $0.00136

Measured 8d ago against content hash 6e7291040528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

improvement-cycles 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/improvement-cycles/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improvement Cycles

Structured templates for running continuous improvement cycles on AI-assisted coding sessions. Adapted from Agent33's improvement-cycle workflows.

Purpose

Improvement cycles provide a repeatable process for:

  • Reviewing session metrics and outcomes
  • Identifying patterns (successes and failures)
  • Generating actionable improvements
  • Tracking improvement adoption over time

Cycle Structure

Each improvement cycle follows four phases:

Phase 1: Metrics Collection

Automated (recommended): Use the session-retrospective-miner skill to generate a structured metrics report with no manual data gathering. The skill uses session_analyze_replay + session_work_ratio MCP tools plus direct JSONL parsing to compute all key metrics and produce actionable findings automatically:

Run session-retrospective-miner with:
  time_window: "last-30-days"  (or match your cycle period)
  project_filter: "all"        (or a specific project slug)
  focus: "all"
Save output to: docs/session-logs/retro-[date].md
Then proceed to Phase 2 using the report as input.

Manual fallback (if session-retrospective-miner or its MCP tools are unavailable):

Gather quantitative data from recent sessions.

Sources:

  • Session replay logs (~/.evokore/sessions/{id}-replay.jsonl)
  • Evidence capture logs (~/.evokore/sessions/{id}-evidence.jsonl)
  • Hook observability logs (~/.evokore/logs/hooks.jsonl)
  • Git history (commits, PRs, branches)

Key Metrics:

Metric Source Description
Tool call count session-replay Total tool invocations per session
Evidence entries evidence-capture Significant operations captured
Damage control triggers damage-control log Blocked or warned operations
Session duration session timestamps Time from first to last tool call
Files modified git diff Scope of changes per session
Test pass rate evidence (test-result) Ratio of passing test runs

Read the full file on GitHub · 187 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 · 187 lines · 14 tokens per session scan A 6e7291040528

Subscribe to this mod's changes

improvement-cycles is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 1,358 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 2026-09-03.

Related

Other skills, from other repositories

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

critique-visual-hierarchy

Critique a rendered screen's hierarchy — entry point, eye flow, weight distribution, and emphasis. Use when attention lands in the wrong place. For establishing hierarchy in new work, use visual-hierarchy (ui-design).

Owl-Listener/designer-skills · 53 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

accessibility-test-plan

Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use accessibility-audit (design-systems).

Owl-Listener/designer-skills · 52 tokens