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 skills add byte5ai/palaia --skill palaia-capturegit clone --depth 1 https://github.com/byte5ai/palaiaWrote 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/byte5ai/palaia/palaia-capture)<a href="https://agentmods.dev/skills/byte5ai/palaia/palaia-capture"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-capture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/byte5ai/palaia/palaia-capture"><img src="https://agentmods.dev/badge/skills/byte5ai/palaia/palaia-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00087 | $0.01094 |
| Opus 5 | $0.00044 | $0.00547 |
| Sonnet 5 | $0.00017 | $0.00219 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
palaia-capture 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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture
This person keeps one memory that every assistant they use can read. Your one job here is to put things into it so they are not lost.
The tool is named after the memory it belongs to — work_memory_capture,
personal_memory_capture. Use the name your client lists. If several are
mounted, pick the one whose purpose covers the subject and use only that one.
It is the only tool to save with. Never write a note and never edit an
existing one to bolt your fact onto it: those notes belong to the person, ten
other sessions may be reading them, and rewriting one to fit something you just
heard is how a memory quietly stops being trustworthy.
The memory's own tool descriptions carry a general note-taking workflow:
search first; write if nothing matches, edit what does. That is for notes
someone asked you to write. It does not apply here. capture is not a lesser
write — it is the only way to add something nobody asked you to add, which is
exactly what everything you pick up in passing is.
Do this before you answer
Before you write your reply, ask: did they just tell me something worth
keeping? If yes, capture it now, then answer. Answering first ends the
turn and loses it.
Acknowledging is not saving. "Got it, you pin that library to 3.4 because 3.5 breaks the parser" and then moving on means the next assistant works it out again next week. Do not ask whether to save it; save it and mention it in one line.
The phrasings that mean something just landed: we settled on, we decided, we went with, because otherwise, that's why, don't do X, it breaks Y, turns out, from now on, actually, no —.
What to capture
- A decision, together with the reason for it.
- A convention: how this team names, formats, structures or ships things.
- A correction from the user. These are the most valuable of all.
- A detail that cost real time to work out and would cost it again.
Skip the conversation itself, anything already in the memory, anything you could look up in seconds, and anything that was plainly thinking aloud.
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.
- 9d ago First seen · 104 lines · 87 tokens per session scan A 7aaed092abb8
palaia-capture is a skill published in the GitHub repository byte5ai/palaia (19 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,094 once invoked, about $0.0004 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
setup
A setup guide for session-recall, a tool that lets an agent search and reuse information from earlier conversations. It covers installation, language, local or cloud processing, and optional team sharing.
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
session-recall
Search the unified local history of past Claude Code, Codex, and Cursor sessions at the START of a task when the user references a prior bug, feature, decision, file, or piece of work. Use before assuming fresh context for prompts such as "remember when…", "we worked on…", "the X bug", "back to…", "what did we decide…
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
create-ex
A guided assistant for turning chat records and personal details about a former partner into a digital persona skill that imitates their communication style. The instructions are in Chinese and describe importing WeChat or iMessage records, analysing them, previewing conversations, and writing a skill file.