save-memory

save-memory is a skill for Claude Code, Codex from sevenschulte/agentic-harness. It costs 74 tokens per session (932 once invoked), scanned A, original, MIT.

A memory-saving workflow for recording durable facts from a coding session in project memory files. It finds the appropriate file, avoids duplicates, and excludes secrets.

In plain words
What is it for?
Use it when the agent should remember a project fact, team convention, user preference, milestone, or other detail for future sessions.
Why use it?
It prevents useful project knowledge and decisions from being lost when a new session starts. Temporary work and sensitive values are kept out of long-term memory.

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/sevenschulte/agentic-harness/save-memory
Any agent
npx skills add sevenschulte/agentic-harness --skill save-memory
Clone the repo
git clone --depth 1 https://github.com/sevenschulte/agentic-harness

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 save-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/sevenschulte/agentic-harness/save-memory.svg)](https://agentmods.dev/skills/sevenschulte/agentic-harness/save-memory)
Your own site
<a href="https://agentmods.dev/skills/sevenschulte/agentic-harness/save-memory"><img src="https://agentmods.dev/badge/skills/sevenschulte/agentic-harness/save-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 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 $0.00074 $0.00932
Opus 5 $0.00037 $0.00466
Sonnet 5 $0.00015 $0.00186
Haiku 4.5 $0.00007 $0.00093

Measured 4d ago against content hash 6246af172383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save-memory 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 4d 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.

.claude/skills/save-memory/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Memory

You are about to persist something learned in this session so it survives into future sessions. This is the deliberate-write step that keeps memory/ current. Without it, the files stagnate and the agent starts every session cold.

Memory files do not self-update. That's the whole point of this skill.

When to save

Save when one of these is true:

  • The user explicitly says "remember X" / "save this" / "note for next time"
  • A durable fact about the codebase, team, or user surfaced this session, something a fresh session would have to re-discover
  • A preference or convention was decided (commit format, branch policy, test approach, naming convention) that isn't yet written down anywhere
  • A project status changed (new project started, milestone hit, blocker resolved)

Do not save:

  • Ephemeral state (current task progress, scratch directories, "where we are right now"). Those belong in ACTIVE.md via the wrap-up skill, not here.
  • The agent's own process narrative ("I ran 5 commands then..."). Save outcomes, not process.
  • Secrets. Ever. Even if the user asks. Redirect to .env.

Step 1 — Read what exists

If the project keeps a knowledge index (.claude/rules/knowledge-index.md or similar), read it. It maps topics to files.

Otherwise, read memory/MEMORY.md and glob memory/**/*.md to see what's already there.

Step 2 — Pick the right file

If the fact is about... Write it to...
Top-level identity, always-true facts about the user/product memory/MEMORY.md
A preference or working-style rule memory/preferences/<topic>.md
A specific project (status, decisions, architecture) memory/projects/<name>/context.md
A research finding worth keeping memory/research/<topic>.md
A codebase convention for a specific language/framework memory/coding-standards/<language>.md

Create new files only when the topic genuinely doesn't fit anywhere existing. One authoritative location per fact; pointers from elsewhere, never copies.

Read the full file on GitHub · 112 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. 4d ago First seen · 112 lines · 74 tokens per session scan A 6246af172383

Subscribe to this mod's changes

save-memory is a skill published in the GitHub repository sevenschulte/agentic-harness (2 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 932 once invoked, about $0.0004 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

llmwiki-query

Answer a question by querying the user's llmwiki. Use when the user asks about their own past work — "what did I decide about X", "what have I been working on", "how did I solve Y", "what's my preferred approach to Z", or any question that the wiki (built from their session history) might answer. Always read the wiki…

Pratiyush/llm-wiki · 87 tokens

aerospace-engineering-technician

Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…

wonsukchoi/domain-experts · 169 tokens

automotive-engineer

Use when a task needs the judgment of an Automotive Engineer — computing weight transfer and tire friction-circle limits for a braking-while-cornering maneuver to set brake-force distribution, sizing a powertrain and gear ratio against a 0-60 mph acceleration target while checking traction versus power limits, sizing…

wonsukchoi/domain-experts · 160 tokens

automotive-engineering-technician

Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…

wonsukchoi/domain-experts · 207 tokens

aviation-inspector

Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs.…

wonsukchoi/domain-experts · 113 tokens

calibration-technician

Use when a task needs the judgment of a Calibration Technologist/Technician — computing a Test Uncertainty Ratio (TUR) and deciding whether it meets the 4:1 target, building a measurement uncertainty budget (Type A/Type B, GUM-style) for a calibration, tracing a reference standard's chain of custody to NIST/SI…

wonsukchoi/domain-experts · 112 tokens