memory-curation

memory-curation is a skill for Claude Code, Codex from Stivi7/cyberpunk-context-runners. It costs 25 tokens per session (278 once invoked), scanned A, original, MIT.

A workflow for deciding whether a project's lasting decisions, reliable patterns, or reusable lessons should be recorded in project memory. It checks the evidence and keeps outdated decisions marked as replaced instead of silently removing them.

In plain words
What is it for?
Use it after reviews, repeated failures, validated conventions, or retrospectives to promote, update, reject, or supersede a memory entry.
Why use it?
It prevents temporary notes, unsupported claims, duplicates, and secrets from becoming long-term guidance. It keeps project memory useful and tied to evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after reviews, repeated failures, validated conventions, or retrospectives to promote, update, reject, or supersede a memory entry.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stivi7/cyberpunk-context-runners/memory-curation
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 Stivi7/cyberpunk-context-runners --skill memory-curation
Clone the repo
git clone --depth 1 https://github.com/Stivi7/cyberpunk-context-runners

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 memory-curation

README.md
[![agentmods](https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/memory-curation/github.svg)](https://agentmods.dev/skills/stivi7/cyberpunk-context-runners/memory-curation)
Your own site
<a href="https://agentmods.dev/skills/stivi7/cyberpunk-context-runners/memory-curation"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/memory-curation/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 memory-curation

Your own site · 80×15
<a href="https://agentmods.dev/skills/stivi7/cyberpunk-context-runners/memory-curation"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/memory-curation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 278 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 $0.00025 $0.00278
Opus 5 $0.00013 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 9d ago against content hash 88e031de5030, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

memory-curation 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 9d 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.

templates/skills/core/memory-curation/SKILL.md · 39 lines

What it actually says

Memory Curation

Metadata

  • Version: 1.0.0
  • Triggers: Retrospective, repeated failure, validated convention, or durable decision
  • Allowed agents: Nexus, Operator, Gatekeeper
  • Side effects: Updates tracked project memory

When to Use

Use after evidence exists. Keep raw attempts in local run state and do not promote ordinary narration.

Inputs

Task evidence, review result, existing decisions, patterns, lessons, project scope, and candidate entry.

Procedure

  1. Classify the candidate as a decision, proven pattern, lesson, or temporary observation.
  2. Reject content that is unsupported, one-off, non-actionable, duplicative, machine-specific, or contains a secret.
  3. Require a lesson to be evidence-backed, generalizable, and actionable.
  4. Merge with an existing entry when possible.
  5. Record scope, evidence, status, and revisit conditions.
  6. Mark contradicted or obsolete entries superseded rather than silently deleting history.

Verification

Gatekeeper confirms evidence, applicability, lack of secrets, and absence of contradiction before promotion.

Output

Promoted, updated, rejected, or superseded entry with rationale and evidence reference.

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. 9d ago First seen · 39 lines · 25 tokens per session scan A 88e031de5030

Subscribe to this mod's changes

memory-curation is a skill published in the GitHub repository Stivi7/cyberpunk-context-runners (4 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 278 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens