memory-retro

A tool for saving lessons and useful insights from completed tasks into an agent's role memory.

In plain words
What is it for?
Use it to record task conclusions, discoveries, and other insights for future work.
Why use it?
It prevents useful experience from being lost when a task ends or a later task begins.

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/dwsy/agent/memory-retro
Any agent
npx skills add Dwsy/agent --skill memory-retro
Clone the repo
git clone --depth 1 https://github.com/Dwsy/agent

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00013 $0.01156
Opus 5 $0.00006 $0.00578
Sonnet 5 $0.00003 $0.00231
Haiku 4.5 $0.00001 $0.00116

Measured 2d ago against content hash d560f3813ae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-retro 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.

extensions/role-persona-old/skills/memory-retro/SKILL.md · 130 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 130 lines · 13 tokens per session scan A d560f3813ae1

Subscribe to this mod's changes

memory-retro is a skill published in the GitHub repository Dwsy/agent (22 stars, last pushed 14d ago), with no licence file. It adds 13 tokens to every session and 1,156 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 2026-08-30.

Related

Other skills, from other repositories

project-orchestration

Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management.

darrenhinde/OpenAgentsControl · 25 tokens

llmtornado-tutorial-generator

Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.

lofcz/LLMTornado · 31 tokens

claude-paper-study

Use this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).

alaliqing/claude-paper · 28 tokens

skmtc-retro

Run a self-retrospective on a SKMTC-related session — generator authoring, CLI configuration, debugging, or any sustained interaction involving @skmtc/core, @skmtc/cli, or @skmtc/gen- packages. Captures three distinct outputs: (1) friction entries (mistakes, surprises, overridden defaults, multi-cycle struggles), (2)…

skmtc/skmtc · 311 tokens

squads-learn

Capture learnings after completing work. Use when finishing a task, fixing a bug, discovering a pattern, or learning something worth remembering for future sessions. Helps build institutional memory.

agents-squads/squads-cli · 41 tokens

skmtc-generator

Author and edit Skmtc generators — packages that project an OpenAPI domain model into application code. Method: clone the nearest stock generator, then apply the engine rules imitation can't teach. Assumes zero prior Skmtc knowledge. Use when asked to "write a skmtc generator", "author/clone/customize gen-x", "add a…

skmtc/skmtc · 110 tokens