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 commands/a777ance/claude-code-homelab/refreshgit clone --depth 1 https://github.com/a777ance/claude-code-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/a777ance/claude-code-homelab/refresh)<a href="https://agentmods.dev/commands/a777ance/claude-code-homelab/refresh"><img src="https://agentmods.dev/badge/commands/a777ance/claude-code-homelab/refresh.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 | $0.00024 | $0.00529 |
| Opus 5 | $0.00012 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
refresh 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 3d 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.
What it actually says
The user wants this session on the latest seed. Ask first — do not clear or read
anything yet. This is the gate that a bare /clear can't offer (by the time /clear's
hook runs, the conversation is already gone).
1. Ask how (one AskUserQuestion, header "Refresh")
- Reseed in place (Recommended) — keep the whole conversation; pull the latest seed and regenerate the briefing on top of it. Nothing is lost.
- Clear + reseed — wipe the conversation first for a clean slate, then reload. In-flight work in this chat is discarded.
2. If "Reseed in place" → do it now, no clear
Run the /reseed logic directly, conversation intact — pull the seed, then read:
-
git fetch origin --quiet, thengit status --short— the tree must be clean. -
git pull --ff-onlyto land the current seed (origin/main) on disk (a "refresh" is really a pull; regenerating from a behind-local seed rebuilds a stale world). Dirty tree or non-fast-forward → do not pull; stop and say so rather than reseeding stale. -
Read the seed in one batch from the now-current tree:
-
CLAUDE.md— the briefing (this repo is a setup guide, not a live system — don't deploy from here). -
README.md— start here. -
docs/ai-cto/context.md— current open items (AI CTO state). -
Confirm in one line: the loaded
CLAUDE.mdrevision + whether the pull fast-forwarded or was already current + "reseeded in place, history kept." Then stop and wait for work.
3. If "Clear + reseed" → hand off to /clear
You cannot invoke /clear yourself — it's a built-in the user must type. Say exactly:
Type
/clearnow — the SessionStart hook will auto-run the sync and reseed.
Then stop. Do not read the seed here; the hook does it on the fresh session.
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.
- 3d ago First seen · 43 lines · 24 tokens per session scan A 741b463d3a7a
refresh is a command published in the GitHub repository a777ance/claude-code-homelab (2 stars, last pushed 23d ago), licensed MIT. It adds 24 tokens to every session and 529 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.