What is memory-hygiene?

Guidance for keeping persistent memory accurate and tidy. It covers finding contradictions, correcting or removing wrong entries, and reviewing the overall health of stored memories.

Use it when retrieved memories conflict, seem outdated, become noisy, or need consolidation after many corrections.

Old or conflicting memories can cause an agent to use the wrong project information. These instructions provide a process for resolving that problem and cleaning up excess automatic records.

How matrixorigin/memoria configures Kiro

Reuse

Borrowing it

Nothing to install: this file belongs to matrixorigin/memoria. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/matrixorigin/memoria/main/.kiro/steering/memory-hygiene.md

Clone the repo

git clone --depth 1 https://github.com/matrixorigin/memoria

Made for: Kiro.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/matrixorigin/memoria/memory-hygiene/github.svg)](https://agentmods.dev/instructions/matrixorigin/memoria/memory-hygiene)

Your own site

<a href="https://agentmods.dev/instructions/matrixorigin/memoria/memory-hygiene"><img src="https://agentmods.dev/badge/instructions/matrixorigin/memoria/memory-hygiene/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/matrixorigin/memoria/memory-hygiene"><img src="https://agentmods.dev/badge/instructions/matrixorigin/memoria/memory-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 598 This file is loaded in full into every session.

When invoked 598 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00598	$0.00598
Opus 5.5	$0.00239	$0.00239
Sonnet 5.5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 1mo ago against content hash d62e4464bb66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-hygiene 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 1mo 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.

.kiro/steering/memory-hygiene.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Hygiene & Self-Governance

Proactive memory health management — don't wait for the user to ask.

Proactive Governance Triggers

Run memory_governance (1h cooldown) when you notice ANY of these:

Retrieval returns clearly outdated or contradictory results
You stored 10+ memories in this session without any cleanup
User mentions memory feels "noisy" or "wrong"

After governance, check the response for:

snapshot_health.auto_ratio > 50% → suggest memory_snapshot_delete(prefix="auto:")
Quarantined memories → inform user what was quarantined and why

Contradiction Resolution

When you detect two memories that contradict each other:

memory_search to find both memories and their IDs
Determine which is newer/more accurate based on timestamps and context
memory_correct the older one with the accurate information, OR
memory_purge the wrong one if it's completely invalid
Never leave both — contradictions poison retrieval

Run memory_consolidate (30min cooldown) when:

You found a contradiction manually
User reports "memory says X but it should be Y" more than once in a session
After a large batch of corrections

Snapshot Hygiene

Snapshots accumulate from auto-saves and safety snapshots. Clean periodically:

memory_snapshots(limit=20)  # check current state

If too many:

memory_snapshot_delete(prefix="pre_") — purge safety snapshots from purge/correct
memory_snapshot_delete(prefix="auto:") — purge auto-generated snapshots
memory_snapshot_delete(older_than="<3 months ago>") — age-based cleanup

Keep named snapshots the user created explicitly.

Entity Graph Maintenance

Entity extraction is automatic — every memory_store triggers regex-based extraction, with LLM extraction as a fallback when configured. No manual intervention needed.

Reflection Cadence

memory_reflect (2h cooldown) synthesizes high-level insights. Suggest it when:

User asks "what patterns do you see" or "summarize what you know"
memory_search returns a high volume of results and no reflection has been done recently
Starting a new project phase — reflect on the previous phase first

Read the full file on GitHub · 71 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.

1mo ago First seen · 71 lines · 598 tokens per session scan A d62e4464bb66

Subscribe to this mod's changes

memory-hygiene is an instructions file published in the GitHub repository matrixorigin/memoria (623 stars, last pushed 2d ago), licensed Apache-2.0. It adds 598 tokens to every session, about $0.0024 per session on Opus 5.5. 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 2026-09-08.

Databases LLM Memory and context agent ai storage

memory-hygiene next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memory-hygienematrixorigin/memoria	Instructions file	623	2d ago	Apache-2.0	A	598	Kiro
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

memoria: Instructions file for Kiro