agentmods.dev

hyper-memory

A tool for finding durable, project-specific knowledge in previous hyperclaude plans, reviews, and research notes. It creates one evidence-based candidate note for each repeated piece of information it finds.

In plain words
What is it for?
Use it after several hyperclaude work cycles have accumulated. It scans the .hyperclaude/ records, can preview candidates without writing them, and saves approved candidates under .hyperclaude/memory/candidates/.
Why use it?
Important lessons can remain buried in old project records. Extracting them makes useful knowledge easier to review and keep for later work.

Skill for Claude CodeCodex

3 14d ago A scan 62 tokens original MIT
View the source file zeikar/hyperclaude
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/zeikar/hyperclaude/hyper-memory
Any agent
npx skills add zeikar/hyperclaude --skill hyper-memory
Clone the repo
git clone --depth 1 https://github.com/zeikar/hyperclaude

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,261 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 $0.00062 $0.01261
Opus 5 $0.00031 $0.00630
Sonnet 5 $0.00012 $0.00252
Haiku 4.5 $0.00006 $0.00126

Measured 2d ago against content hash d74b132b7fc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hyper-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 2d 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.

skills/hyper-memory/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hyper-memory

Repo-local knowledge extraction. Scans the accumulated .hyperclaude/ corpus and writes one evidence-anchored candidate markdown file per deterministic copy-based span under .hyperclaude/memory/candidates/. v1 is extraction + curation only — auto-injection into future sessions is the v2 north star and is explicitly out of scope here.

When to use

  • User typed /hyperclaude:hyper-memory (with or without an argument).
  • A batch of work has accumulated in .hyperclaude/ (several archived plans, plan-reviews, research artifacts) and it's worth mining for durable repo-local knowledge.

When to skip

  • Only a single small artifact exists since the last extraction — not enough accumulated corpus to be worth mining.
  • You want the knowledge injected automatically into a session — that's v2, not implemented.

How it works

  1. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/memory/extract.mjs" via Bash and parse the one-line JSON summary it prints to stdout: { ok, scanned, candidates, written, skipped, errored, candidatesDir }.

    The script's CLI accepts exactly two flags — no others exist:

    • --dry-run — compute candidates and keys but write nothing (written is always 0).
    • --root <path> — corpus root to scan (default .hyperclaude).

  2. It fully enumerates the v1 source allowlist — NOT newest-only:

    • plans/done/ — every archived plan.
    • plan-reviews/ — every plan-review artifact whose verdict is Ship as-is.
    • research/ — every research artifact.

    code-reviews/ and docs-reviews/ are v1 non-goals and are never scanned.

  3. It writes one evidence-anchored markdown file per candidate under .hyperclaude/memory/candidates/, keyed by a compound hash so re-runs are idempotent: a candidate is skipped if its key already exists in EITHER .hyperclaude/memory/candidates/ OR .hyperclaude/memory/promoted/ — an already-promoted candidate is never resurrected.

Candidate schema

Each candidate file's YAML frontmatter carries exactly these keys, in this order:

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 62 tokens per session scan A d74b132b7fc3

Subscribe to this mod's changes

hyper-memory is a skill published in the GitHub repository zeikar/hyperclaude (3 stars, last pushed 14d ago), licensed MIT. It adds 62 tokens to every session and 1,261 once invoked, about $0.0003 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.

Memory and contextResearchWriting and docsagent-skillsclaudeclaude-aiclaude-codeclaude-code-pluginclaude-skills
Related

Other skills, from other repositories

r3f-animation

React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.

zebbern/claude-code-guide · 43 tokens

workflow

Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.

UfoMiao/zcf · 25 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

agile-product-owner

../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

golden-chat-topics

Use when testing the goldenchattopics golden build.

yusufkaraaslan/Skill_Seekers · 15 tokens