Borrowing it
Nothing to install: this file belongs to jnerytech/specd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jnerytech/specd/main/.claude/skills/claude-code-memory/SKILL.mdgit clone --depth 1 https://github.com/jnerytech/specdWrote 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.
[](https://agentmods.dev/skills/jnerytech/specd/claude-code-memory)<a href="https://agentmods.dev/skills/jnerytech/specd/claude-code-memory"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/claude-code-memory/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.
<a href="https://agentmods.dev/skills/jnerytech/specd/claude-code-memory"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/claude-code-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00079 | $0.02092 |
| Opus 5.5 | $0.00032 | $0.00837 |
| Sonnet 5.5 | $0.00016 | $0.00418 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
claude-code-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How Claude Remembers Your Project
Source: Claude Code docs — code.claude.com/docs/en/memory | Sections: 8 | Generated: 2026-06-23
How to Use This Skill
- Without arguments — load core frameworks for reference
- With a topic — ask about
load order,path-scoped rules,auto memory,claudeMdExcludes,@imports; I find and read the relevant chapter - With chapter — ask for
ch05; I load that specific chapter - Browse — ask "what chapters do you have?" for the full index
When you ask about a topic not covered below, I read the relevant chapter file before answering.
Core Frameworks & Mental Models
Two-mechanism memory model. A session starts with a fresh context window; knowledge persists via exactly two systems, both loaded every session:
- CLAUDE.md — instructions you write (loaded in full).
- Auto memory — notes Claude writes itself (per repo;
MEMORY.mdindex loads up to 200 lines / 25KB).
You own CLAUDE.md; Claude owns auto memory. Match the writer to the knowledge.
Context, not enforcement. Both systems are content Claude reads and tries to follow — no strict compliance. For a guaranteed action at a lifecycle point, use a hook, not memory. CLAUDE.md is delivered as a user message after the system prompt; --append-system-prompt puts text at system-prompt level (every invocation).
Right-mechanism routing (where does a fact go?):
- Same mistake twice / re-typed correction / new-teammate context → CLAUDE.md.
- Multi-step procedure → skill. Only matters for some files/dirs → path-scoped rule (
.claude/rules/+paths). Global always-true fact → root CLAUDE.md. - Claude discovered it, should accrue automatically → auto memory. Must happen at lifecycle point → hook. Hard block → managed setting (
permissions.deny).
Four-scope hierarchy (load order: broadest first, closest-to-CWD read last → wins on conflict): managed policy → user (~/.claude/CLAUDE.md) → project (./CLAUDE.md or ./.claude/CLAUDE.md) → local (./CLAUDE.local.md, gitignored). All files concatenate, none override. Ancestors load eagerly at launch; subdirectory files load lazily when Claude reads a file there.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- chapters/ch01-claude-md-vs-auto-memory.md 3.6 KB
- chapters/ch02-writing-effective-claude-md.md 4.1 KB
- chapters/ch03-locations-and-load-order.md 4.5 KB
- chapters/ch04-imports-and-agents-md.md 4.2 KB
- chapters/ch05-project-rules.md 4.5 KB
- chapters/ch06-managing-for-large-teams.md 4.6 KB
- chapters/ch07-auto-memory.md 4.4 KB
- chapters/ch08-troubleshooting.md 4.9 KB
- cheatsheet.md 3.6 KB
- glossary.md 4.2 KB
- patterns.md 4.1 KB
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.
- 12d ago First seen · 111 lines · 79 tokens per session scan A 9e0d98aace37
claude-code-memory is a skill published in the GitHub repository jnerytech/specd (0 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,092 once invoked, about $0.0003 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 2026-10-02.
Other skills, from other repositories
gsd-graphify
Build, query, and inspect the project knowledge graph in .planning/graphs/.
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
gsd-mempalace-recall
Recall decisions, patterns, and surprises from MemPalace before planning.
kiro-steering-custom
Create custom steering documents for specialized project contexts.
kiro-steering
Manage {{KIRODIR}}/steering/ as persistent project knowledge.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.