reflect-and-learn

A review step that turns a successful CodeCortexLoop Direct-mode fix into a written summary and a reusable entry in its playbook. The saved entries are suggestions that need further evidence before becoming trusted.

In plain words
What is it for?
Use it after a successful Direct-mode repair, or run it manually to document the problem, the fix, and the general pattern that can help with similar issues.
Why use it?
It prevents useful lessons from being lost after a fix while reducing the risk of blindly repeating an old solution.

Skill for Claude CodeCodex

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 skills/whitequeen306/code-cortex-loop/reflect
Any agent
npx skills add whitequeen306/code-cortex-loop --skill reflect
Clone the repo
git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,186 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 $0.00048 $0.02186
Opus 5 $0.00024 $0.01093
Sonnet 5 $0.00010 $0.00437
Haiku 4.5 $0.00005 $0.00219

Measured 2d ago against content hash d65eea52a7ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflect-and-learn 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 2d 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/reflect/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect and Learn

CodeCortexLoop v2.2 — turn successful Direct fixes into reusable playbook memory.

Overview

After a Direct-mode run (or manual reflect), produce a human retrospective and a structured reflection that playbook.mjs record can upsert into .cortexloop/playbook.json.

Playbook entries are recall, not authority — new entries start as candidate until diverse verified evidence promotes them. Never skip analysis or blindly apply stored fixes.

Scope (what this skill covers)

Topic Authoritative doc
When to run reflect, skip conditions, Step 6 gates (learning.enabled, Direct + re-verify) commands/cortexloop.md
Manual /cortexloop-reflect orchestration commands/cortexloop-reflect.md
Playbook trust model, signature, tiers, feedback / prune rules/learning-loop.mdc

This skill covers only: how to extract generalizable patterns from a successful fix session and write high-quality 08-reflection.md + reflection.json. Do not duplicate CLI or trust-model details here — follow the table above when those questions arise.

When to Use

  • Automatically after CodeCortexLoop Direct mode completes re-verification successfully (orchestrator loads this skill in Step 6)
  • Manually via /cortexloop-reflect when you want to capture learnings from a recent fix session
  • When you have evidence of what was fixed (ideally docs/cortexloop/report.json + git diff)

When NOT to use:

  • Report-only runs with no fixes applied
  • Failed or incomplete Direct runs (tests still failing)
  • One-off project-specific hacks that cannot generalize

Inputs

Read before writing:

  1. docs/cortexloop/report.json — findings marked fixed, before/after scores
  2. Git diff of changes applied in Direct mode (diff wins if it disagrees with the report)
  3. .cortexloop/playbook.json — skim existing entries for authoring-time dedup
  4. cortexloop.config.jsonlearning block (paths, global flag) — for record flags only
  5. rules/learning-loop.mdc — when unsure whether something belongs in playbook memory

Read the full file on GitHub · 198 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. 2d ago First seen · 198 lines · 48 tokens per session scan A d65eea52a7ec

Subscribe to this mod's changes

reflect-and-learn is a skill published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,186 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens