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/abilityai/abilities/setup-memorynpx skills add Abilityai/abilities --skill setup-memorygit clone --depth 1 https://github.com/Abilityai/abilitiesWhat 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 | $0.00011 | $0.00778 |
| Opus 5 | $0.00005 | $0.00389 |
| Sonnet 5 | $0.00002 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
setup-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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup JSON Memory
Initialize a structured JSON memory system for persistent agent state.
Step 1: Ask Configuration
Use AskUserQuestion:
Question 1: "What type of agent is this memory for?"
- Options:
- "Business assistant" - Profile, entities, tasks focus
- "Personal assistant" - Preferences, reminders focus
- "Technical agent" - Context, project tracking focus
- "General purpose (Recommended)" - All sections
Question 2: "Should the memory track action history?"
- Options:
- "Yes (Recommended)" - Creates action_log.txt
- "No" - Memory only, no action log
Step 2: Create Directory Structure
mkdir -p memory
Step 3: Create Memory Index
Write memory/memory_index.json:
{
"metadata": {
"schema_version": "1.0",
"created": "[ISO timestamp]",
"last_updated": "[ISO timestamp]",
"total_interactions": 0
},
"profile": {
"name": null,
"role": null,
"context": null
},
"preferences": {
"communication_style": null,
"tools": []
},
"memory": {
"key_facts": [],
"decisions": [],
"project_overviews": []
},
"context": {
"active_topics": [],
"recent_work": [],
"scratchpad": null
},
"entities": [],
"tasks": {
"active": [],
"completed": []
},
"custom": {}
}
Step 4: Create Action Log (if enabled)
Write memory/action_log.txt:
# Action Log
# Format: YYYY-MM-DD HH:MM:SS - Action description
# Newest entries at top
[ISO timestamp] - Memory system initialized
Step 5: Create Memory Map
Write memory/memory_map.yaml:
# Memory System Map
# High-signal index of memory components
memory_index:
path: memory/memory_index.json
load: selective # Use jq queries, not full load
sections:
- profile
- preferences
- context
- entities
action_log:
path: memory/action_log.txt
load_lines: 50 # Most recent entries
custom_files: []
Step 6: Update CLAUDE.md
Add memory configuration:
## Memory System
JSON-based persistent memory in `memory/` folder.
### Loading Memory
Use `/load-memory` to load context at session start.
Load selectively - don't read entire memory_index.json.
### Updating Memory
Use `/memory-jq` for efficient field updates.
Use `/update-memory` after significant changes.
### Memory Sections
- `profile` - User/agent identity
- `preferences` - Settings and styles
- `memory.key_facts` - Important facts to remember
- `context` - Current work state
- `entities` - People, projects, orgs
- `tasks` - Active and completed items
### Action Log
`memory/action_log.txt` - Reverse chronological action history.
Newest entries at top. Load last 50 lines for context.
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.
- yesterday First seen · 146 lines · 11 tokens per session scan A b9fda2bf9057
setup-memory is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 11 tokens to every session and 778 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…