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/session-startnpx skills add IlyaGorsky/memory-toolkit --skill session-startgit 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 | $0.01481 |
| Opus 5 | $0.00011 | $0.00740 |
| Sonnet 5 | $0.00004 | $0.00296 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
session-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/session-start — Cold session start
Quick context entry. Gather state, propose focus.
Step 1: Gather context
Do NOT re-read MEMORY.md — already in system prompt via claudeMd loader.
If a workstream argument is provided — skip to Step 3.
MEM="${CLAUDE_PLUGIN_ROOT}/scripts/memory.js"
PROJ_KEY=$(pwd | tr '/.' '-' | sed 's/^-//')
MEM_DIR="$HOME/.claude/projects/-${PROJ_KEY}/memory"
# Latest handoff (global; per-workstream fetched in Step 3)
node "$MEM" --dir="$MEM_DIR" handoff
# Latest dated note
ls -t "$MEM_DIR/notes/"*.md 2>/dev/null | head -1 | xargs -I{} head -30 {}
# Workstreams sorted by aggregate weight
node "$MEM" --dir="$MEM_DIR" workstreams
# Top-3 brief inline
for WS in <top-3 from sorted list>; do
node "$MEM" --dir="$MEM_DIR" workstream "$WS" --brief | head -15
done
Decision tree — source of focus candidates:
| Handoff state | Candidates source |
|---|---|
| ≤7 days old, has "What's next" | Handoff primary (workstreams table still rendered for context) |
| >7 days old | Workstreams table; handoff shown as stale context |
Missing/empty/only SESSION_START markers |
Workstreams table; say "no usable context", suggest /session-restore |
| No handoff, no notes | Workstreams table only |
The workstreams table in Step 1b is always rendered in Step 4 — it's the session's map, not a fallback. The decision tree only controls where focus candidates come from.
Step 1b: Workstreams table (always rendered)
Render as table. Top-3 rows show synthesized "What's in" from --brief; rest show keywords. ➕ row is mandatory.
**Workstreams** (sorted by aggregate weight)
| # | Workstream | Last touched | What's in / Keywords |
|---|---|---|---|
| 1 | <name> | <date> | <synthesized 1-line for top-3> |
| ... | | | <keywords for rest> |
| N | ➕ Create new | | |
If user picks ➕ — ask name + keywords, then:
node "$MEM" --dir="$MEM_DIR" add-workstream <name> <keyword1> <keyword2> ...
Step 2: Git status
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.
- 3d ago First seen · 177 lines · 22 tokens per session scan A 1061815749a0
session-start 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 1,481 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.