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 xg-gh-25/SwarmAI --skill s_save-activitygit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_save-activity)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_save-activity"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_save-activity/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/xg-gh-25/swarmai/s_save-activity"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_save-activity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00656 |
| Opus 5 | $0.00023 | $0.00328 |
| Sonnet 5 | $0.00009 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
save-activity 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Activity
Extract key points from the current conversation and append them to today's DailyActivity file. This is the on-demand counterpart to the automatic post-session-close extraction hook.
When to Use
The user explicitly asks to save activity:
- "save activity"
- "save daily activity"
- "log today's activity"
- "write daily activity"
How to Save
Step 1: Gather conversation context
Review the current conversation and identify:
- Topics: What subjects were discussed
- Decisions: What choices or recommendations were made
- Files Modified: What files were created, edited, or read
- Open Questions: What remains unresolved
Step 2: Write the DailyActivity entry
Write a structured entry to Knowledge/DailyActivity/YYYY-MM-DD.md (today's date)
using this format:
## Session — HH:MM | session_id | Title
### What Happened
- Topic 1
- Topic 2
### Key Decisions
- Decision 1
### Files Modified
- path/to/file1
- path/to/file2
### Open Questions
- Question 1
If the file already exists, append the new session entry — do not overwrite.
Update the sessions_count in the YAML frontmatter.
If the file does not exist, create it with frontmatter:
---
date: "YYYY-MM-DD"
sessions_count: 1
distilled: false
---
Step 3: Confirm to user
After writing, briefly confirm:
- "Saved activity to Knowledge/DailyActivity/2025-07-15.md"
Keep confirmation to one line.
Rules
- Append only — never overwrite existing DailyActivity content
- Be concise — summarize, don't dump raw conversation
- Use consistent format — always include all 4 subsections
- Deduplicate — don't repeat topics or files already in today's entry
- Read before write — always read the existing file first, then append using the Write tool with the full content (read + new entry). This prevents race conditions with the backend's automatic DailyActivity extraction hook which may write simultaneously at session close
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.
- 12d ago First seen · 89 lines · 46 tokens per session scan A 6bace02e6c06
save-activity is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 656 once invoked, about $0.0002 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
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
why
Explain the provenance, authority, expiry, degradation state, and token accounting of CIGAR context already presented in this session.
checkpoint
Create an inspectable CIGAR checkpoint before compaction, interruption, or a meaningful task boundary.
memo-bank-query
Load the governing spec/contract for a file or topic from a project's memo-bank (a read-only MCP docs corpus) BEFORE reading code or editing. Use this in any repo that has a .island-slices.json or a memo-bank MCP server, whenever you are about to edit a file, or are asked "what governs X", "is there a spec for Y"…
audit-knowledge
Scan Antigravity conversation transcript + artifact directory for extractable knowledge. Use when user asks for 'knowledge audit', 'audit knowledge', 'check for extractable knowledge', 'scan transcript', or at session start when audit cadence is exceeded.
handoff
Generate a passoff package so the next reader can pick up cleanly — for future-you in a new session (typically when context is high and you need to restart) or for a coworker (via brief mode). Default + auto modes emit a paste-ready next-session opener as the headline artifact, alongside PROGRESS / CLAUDE / memory…