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/update-memorynpx skills add Abilityai/abilities --skill update-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 | $0.00013 | $0.00513 |
| Opus 5 | $0.00006 | $0.00257 |
| Sonnet 5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
update-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Update Memory
Update the memory system after a session with new information.
Step 1: Update Action Log
Prepend new actions to memory/action_log.txt:
# Get current timestamp
timestamp=$(date '+%Y-%m-%d %H:%M:%S')
# Prepend new entry (newest at top)
echo "$timestamp - [Action description]" | cat - memory/action_log.txt > tmp.txt && mv tmp.txt memory/action_log.txt
Format each action as:
YYYY-MM-DD HH:MM:SS - Brief description of what was done
Step 2: Update Context
Update current work state:
jq '.context.recent_work = ["task1", "task2"] | .context.active_topics = ["topic1"]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json
Step 3: Add Key Facts (if learned)
If new important facts were learned:
jq '.memory.key_facts += ["New important fact"]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json
Step 4: Update Entities (if new)
If new people/projects/orgs were encountered:
jq '.entities += [{"type": "person", "name": "Name", "relationship": "role", "added": "YYYY-MM-DD"}]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json
Step 5: Record Decisions (if made)
If significant decisions were made:
jq '.memory.decisions += [{"date": "YYYY-MM-DD", "decision": "What was decided", "rationale": "Why"}]' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json
Step 6: Update Metadata
Always update timestamps and counters:
jq '.metadata.last_updated = now | todate | .metadata.total_interactions += 1' memory/memory_index.json > tmp.json && mv tmp.json memory/memory_index.json
Step 7: Report
Summarize what was updated:
- X actions logged
- X new facts added
- X entities updated
- Metadata timestamp refreshed
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 · 74 lines · 13 tokens per session scan A 204836fe0555
update-memory is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 13 tokens to every session and 513 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…