eg-memsync

eg-memsync is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 93 tokens per session (1,333 once invoked), scanned A, original, Apache-2.0.

A reconciliation process for an agent's saved memory and a project's governance documents. Governance documents are files such as AGENTS.md or .agent/rules.md that define how work should be done.

In plain words
What is it for?
Use it to compare project memory with governance files, correct the outdated side, and promote durable memory-only policies into the documents.
Why use it?
It finds policies that conflict, became outdated, or exist only in memory, so future sessions do not have to guess which instruction is current.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the estregenesis plugin — 13 skills shipped together

Good fit Use it to compare project memory with governance files, correct the outdated side, and promote durable memory-only policies into the documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/eg-memsync
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 SoliEstre/EstreGenesis --skill eg-memsync
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install estregenesis, the plugin that ships this one along with the rest of its 13 skills.

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 eg-memsync

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-memsync.svg)](https://agentmods.dev/skills/soliestre/estregenesis/eg-memsync)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/eg-memsync"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-memsync.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,333 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 $0.00093 $0.01333
Opus 5 $0.00046 $0.00666
Sonnet 5 $0.00019 $0.00267
Haiku 4.5 $0.00009 $0.00133

Measured 8d ago against content hash 267d4c7df629, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eg-memsync 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.

plugins/estregenesis/skills/eg-memsync/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/eg-memsync (/egmem) — reconcile agent memory ↔ project docs

Agent memory and project docs drift apart in both directions, and each direction is a real failure mode. Memory absorbs corrections faster than docs do — so a doc keeps stating a policy that a dated memory has since revised, sometimes while citing that very memory file by name. And docs (plus the repo itself) move on while memory keeps stale state — a memory still "waiting" on a gate that was resolved dozens of releases ago, or an index whose one-line summaries no longer match the files they index. Either way the next session inherits a contradiction and has to guess. This skill is the periodic true-up.

0. Locate the two corpora

  • Memory — the per-project agent memory store: on Claude Code, the project's auto-memory directory (memory/*.md plus its index file); otherwise the workspace's memory/feedback_*.md convention or the harness equivalent. No memory store → nothing to reconcile. Say so and stop — do not invent one.
  • Docs — the project's governance surfaces: AGENTS.md (the SSoT), .agent/rules.md (operational detail), and the per-tool bridge files (CLAUDE.md and friends). A project not on the AGENTS.md pattern routes to /eg-migration first; a project with no seed at all routes to /eg-bootstrap.

Read both corpora fully before judging anything — drift detection on a partial read produces false confidence.

1. Detect drift — five kinds

Sweep every memory file against every doc section (and the memory index against its own files):

  • (a) memory supersedes doc — a doc states a policy that a dated memory has since revised. The strongest tell: the doc cites the memory file by name while carrying the pre-revision content.
  • (b) dangling references — a doc cites a memory file, directory, or convention that does not exist (or no longer does); a memory wikilink points at a renamed or missing target; a placeholder link was never filled in.
  • (c) memory-only durable policy — an operating rule (a restart procedure's required environment, a deploy-drift caveat, a content-tone standard, a routing rule) that lives only in memory with no doc surface. These are the promotion candidates.
  • (d) duplicated content where one copy went stale — the same fact stated in both places with different values. The memory index counts: an index entry that summarizes an older revision of its own file is this kind.
  • (e) outdated identifiers — versions, dates, paths, counts that one side visibly outgrew. Internal contradictions inside a single doc (two sections quoting two different versions of the same thing) count too.

Read the full file on GitHub · 48 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 · 48 lines · 93 tokens per session scan A 267d4c7df629

Subscribe to this mod's changes

eg-memsync is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,333 once invoked, about $0.0005 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

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens

wiki

Use this skill when querying workspace knowledge before tasks or running mandatory post-review ingest evaluation and conditional wiki ingestion. Self-learning loop for the workspace.

wcgomes/agents-workspace · 30 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens

moai-foundation-context

Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.

modu-ai/moai-adk · 41 tokens