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_memory-distillgit 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_memory-distill)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_memory-distill"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_memory-distill/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_memory-distill"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_memory-distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 111 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00048 | $0.01430 |
| Opus 5 | $0.00024 | $0.00715 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
memory-distill 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 11d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Distill
Distill raw DailyActivity logs into curated MEMORY.md entries. This skill runs automatically and silently — never announce, never ask permission.
1. Detection
Scan Knowledge/DailyActivity/*.md for unprocessed files:
- List all
.mdfiles inKnowledge/DailyActivity/ - For each file, read the YAML frontmatter (delimited by
---lines at the top) - A file is unprocessed if it has no frontmatter OR lacks
distilled: true - Count unprocessed files
- If count ≤ 3, exit silently — not enough material to distill
Do not announce the scan or its results.
2. Extraction
For each unprocessed DailyActivity file, extract:
- Key decisions — Architecture choices, tool selections, approach changes
- Lessons learned — What worked, what didn't, debugging insights
- Recurring themes — Patterns across multiple sessions
- User corrections — Times the user corrected your output or approach
- Error resolutions — Problems encountered and their fixes
Skip one-off observations, transient context, and information already captured in KNOWLEDGE.md or other context files.
3. Writing to MEMORY.md
Write distilled content to the appropriate sections of MEMORY.md:
-
Use the Edit tool for all MEMORY.md writes — never use
python3 locked_write.pyvia Bash (crashes in PyInstaller bundles). Always prefix entries with the source DailyActivity date (not today's date). Read.context/MEMORY.md, find the target section, and prepend the new entry at the top of the section (after the##heading). Format:- YYYY-MM-DD: <distilled entry> -
Map extracted content to MEMORY.md sections:
- Key decisions →
## Key Decisions - Lessons learned →
## Lessons Learned - Recurring themes →
## Patterns and Preferences - User corrections →
## Lessons Learned - Error resolutions →
## Lessons Learned - Current work status →
## Recent Context - Open thread updates →
## Open Threads
- Key decisions →
-
Fallback: If a target section is not found (user may have renamed or removed it), add a new
## Distilledsection at the end of the file and write there. -
Never remove existing MEMORY.md content — only prepend or append to sections
-
Keep entries concise: one line per decision/lesson, date-prefixed, grouped by theme
-
Deduplication: Before writing, check if the same content (ignoring date prefix) already exists in the target section. Skip duplicates.
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.
- 11d ago First seen · 152 lines · 48 tokens per session scan A 8325a907f2ee
memory-distill is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,430 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.
audit-share
Batch-review personal knowledge for promotion to team-shared project knowledge. Walks insights/decisions/approaches/rules and IDEAS-BACKLOG.md entries, recommends a target project-knowledge/ destination per item, and lets the user approve all/numbers/modify/skip. Use when user says '/audit-share', '/share-audit'…