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.
git clone --depth 1 https://github.com/jmagar/claude-homelabWrote 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/commands/jmagar/claude-homelab/save-to-md)<a href="https://agentmods.dev/commands/jmagar/claude-homelab/save-to-md"><img src="https://agentmods.dev/badge/commands/jmagar/claude-homelab/save-to-md/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/commands/jmagar/claude-homelab/save-to-md"><img src="https://agentmods.dev/badge/commands/jmagar/claude-homelab/save-to-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00009 | $0.00981 |
| Opus 5 | $0.00005 | $0.00491 |
| Sonnet 5 | $0.00002 | $0.00196 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
save-to-md 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session Documentation
Document the entire conversation session (not just recent work) as a markdown file at $ARGUMENTS. If no path is provided, save to docs/sessions/YYYY-MM-DD-description.md in the current working directory.
Path safety rules:
- Keep this workflow in-repo. If the target is outside the current repo root, stop and report the path issue.
- If the target filename already exists, do not overwrite. Append a suffix like
-v2,-v3, etc.
Documentation Requirements
Include in the markdown file:
- Session Overview: Brief summary of what was accomplished
- Timeline: Chronological breakdown of major activities
- Key Findings: Important discoveries with file paths and line numbers where relevant
- Technical Decisions: Reasoning behind implementation choices
- Files Modified: List of all files created/modified with purpose
- Commands Executed: Critical bash commands and their results
- Behavior Changes (Before/After): User-visible or system-visible behavior changes caused by this session
- Verification Evidence: Table with
command | expected | actual | status - Source IDs + Collections Touched: Every embed/retrieve source ID and collection used, with outcome
- Risks and Rollback: Concise risk notes and rollback path for non-trivial changes
- Decisions Not Taken: Alternatives considered but rejected, with brief rationale
- Open Questions: Unresolved items or assumptions that need follow-up
- Next Steps: Any remaining tasks or follow-up items
Content quality rules:
- Facts only. Do not infer values that were not observed in tool/command output.
- If something is uncertain, place it in Open Questions instead of stating it as fact.
- Keep sections concise (target max 5 bullets per section), but exceed when needed to preserve material implementation details, critical evidence, or safety context.
- Use file:line references (e.g.,
server.ts:45) for code-specific findings.
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 · 77 lines · 9 tokens per session scan A 3c52bc62a8b5
save-to-md is a command published in the GitHub repository jmagar/claude-homelab (78 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 981 once invoked, about $0.0000 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 commands, from other repositories
context-save
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
handoff
Create a handoff document for seamless session continuity.
memory-review
Display current memory state with timestamps, sizes, and staleness indicators.
index
Create persistent project understanding via PROJECTMAP.md.