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/reikor-arg/inmemory/designnpx skills add Reikor-Arg/inmemory --skill designgit clone --depth 1 https://github.com/Reikor-Arg/inmemoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/reikor-arg/inmemory/design)<a href="https://agentmods.dev/skills/reikor-arg/inmemory/design"><img src="https://agentmods.dev/badge/skills/reikor-arg/inmemory/design.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.00939 |
| Opus 5 | $0.00030 | $0.00469 |
| Sonnet 5 | $0.00012 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
design 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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designing and reviewing UI
First, read what already exists
A component that is beautiful and unlike everything around it has made the product worse. Before designing anything, find the conventions already in the repo — they outrank any principle below:
node ${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs map # where components live
node ${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs map <Component> # a similar one to match
node ${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs decide --list # design decisions already made
Read one or two existing components in full. Match their spacing scale, their naming, their approach to state and variants. Consistency with mediocre conventions beats excellence in isolation — and if the conventions are genuinely bad, that is a separate conversation to have explicitly, not to resolve by quietly diverging in one file.
What actually makes UI look amateur
Almost always one of these, in this order:
Inconsistent spacing. Pick one scale (4 / 8 / 12 / 16 / 24 / 32 / 48) and
never use a value outside it. Arbitrary padding: 13px reads as sloppy even to
people who cannot name why. This single rule fixes more perceived quality than
any colour choice.
No type hierarchy. Three sizes minimum, with real distance between them — 14 / 20 / 32, not 15 / 16 / 18. Weight and colour carry hierarchy as much as size; a heading that is only 2px larger is not a heading.
Too many colours, too little contrast. One accent, one neutral ramp, and semantic colours only where they mean something. Body text below 4.5:1 contrast is unreadable for a real fraction of users and looks washed out to everyone else.
No breathing room. Cramped is the most common failure by a wide margin. When something looks wrong and you cannot say why, add space before adding anything else.
Everything the same visual weight. If the primary action does not stand out in a squint test, the layout has no hierarchy. Exactly one primary action per view.
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.
- 4d ago First seen · 88 lines · 59 tokens per session scan A 99a33b2a7ed9
design is a skill published in the GitHub repository Reikor-Arg/inmemory (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 939 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.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.