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.
npx agentmods add skills/ilyagorsky/memory-toolkit/memorynpx skills add IlyaGorsky/memory-toolkit --skill memorygit clone --depth 1 https://github.com/IlyaGorsky/memory-toolkitWhat 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 | $0.00022 | $0.01477 |
| Opus 5 | $0.00011 | $0.00739 |
| Sonnet 5 | $0.00004 | $0.00295 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/memory — Project Memory
Step 0: Resolve memory directory
# Claude Code uses git root (not cwd) and replaces / and . with - for project key
GIT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
PROJ_KEY=$(echo "$GIT_ROOT" | tr '/.' '-' | sed 's/^-//')
MEM_DIR="$HOME/.claude/projects/-${PROJ_KEY}/memory"
Resolve memory.js:
MEM="${CLAUDE_PLUGIN_ROOT}/scripts/memory.js"
If not initialized (no memory.js and no plugin found)
Bootstrap for this project:
- Create memory dir:
mkdir -p "$MEM_DIR" - Do NOT copy
memory.jsif the plugin is installed — use$MEMresolved above. Only copy if plugin is not installed and no$MEMfound. - Ask: "What workstreams does the project have?" → create
workstreams.json - Ask: "Describe your role in 1-2 sentences" → Profile
- Ask: "Key links?" → Reference
- Create MEMORY.md:
# {Project} — Memory
## API
\```bash
node {absolute $MEM path} --dir={MEM_DIR} <command>
\```
## Profile
{user answer}
## Rules
### Save
- Decision with reasoning → memory file with **Why:** and **How to apply:**
- User corrects you or confirms non-obvious choice → feedback memory
- Something surprising or counter-intuitive → note + memory
- Convert relative dates to absolute: "Thursday" → "2026-04-10"
### Don't save
- What git log already knows (commits, who changed what)
- What the code already shows (patterns, architecture)
- What CLAUDE.md already says
- Ephemeral task state (use TodoWrite)
### Format
- MEMORY.md = index only, max 200 lines. Details in separate .md files
- Each .md file has frontmatter: name, description, type (feedback/project/user/reference)
- workstreams.json = source of truth for aliases
- Use --brief for quick overviews, full output only when needed
### Session lifecycle
- Start of work → /session-start or /session-continue
- Ideas for later → /park (don't lose the thought)
- After big block of work → /reflect (workarounds, repetitions, insights → backlog)
- Before compact: save key decisions + update handoff
- Long session + topic changed → suggest /session-end
- End of work → /session-end (handoff for next session)
## Reference
{user links}
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.
- 2d ago First seen · 203 lines · 22 tokens per session scan A ec3554f23357
memory is a skill published in the GitHub repository IlyaGorsky/memory-toolkit (13 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,477 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
math-unicode
Use when a response needs mathematical notation (equations, filters, set-builder notation, statistics, calculus, linear algebra, logic, ratios, drops, counts) and the output goes to a terminal or TUI that cannot render LaTeX: Claude Code, Codex CLI, SSH and tmux sessions, CI logs. Load it before composing, including…
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
anatomia-cc
ES: Te dice qué construir en Claude Code y te da el esqueleto de archivos: skill y en qué modo, subagente, hook, servidor MCP, plugin, rutina, artefacto, app con el Agent SDK, una línea en CLAUDE.md, o nada. Corré esto antes del primer archivo. Se dispara con «esto lo hago como skill o como agente», «necesito un MCP o…
create-agents-md
Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance.
create-checkpoint
Capture the current session state as a checkpoint artifact per spec section 4.4. Use when the user signals session end or explicitly requests a checkpoint. Do not use mid-session or without user approval.