Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AlexK020908/infra-designer/plugin install infra-designerWrote 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/alexk020908/infra-designer/refresh-knowledge)<a href="https://agentmods.dev/commands/alexk020908/infra-designer/refresh-knowledge"><img src="https://agentmods.dev/badge/commands/alexk020908/infra-designer/refresh-knowledge.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 5.1 | $0.00014 | $0.00435 |
| Opus 5 | $0.00007 | $0.00217 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
refresh-knowledge 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 5d 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
Refresh knowledge
The plugin's knowledge (cost figures, service limits, "numbers to know", best-practice rules) drifts over time. This command finds stale files and updates them from authoritative sources. $ARGUMENTS
1. Find what's stale
python ${CLAUDE_PLUGIN_ROOT}/engine/cli.py stale
This lists files whose reviewed_at (in knowledge/freshness.json) is past their
refresh_after_days, plus the authoritative verify sources. If nothing is stale, say so
and stop. If the user named a specific file/topic, refresh that even if not yet overdue.
2. Research and update each stale file
For each stale file, if you have web access:
- Read the file to see the specific numbers/limits/claims it makes.
- Verify each against the authoritative sources listed by
stale(AWS pricing / what's-new / docs; Vercel / Supabase docs). Never cite third-party "study guide" sites. - Edit the file in place where a value or recommendation has actually changed. Preserve structure and voice; change facts, not prose for its own sake. If a value is unchanged, leave it.
- Note any change worth flagging (e.g. a price drop that changes a default).
If you do not have web access, list the stale files and their verify sources and stop — do not invent numbers.
3. Bump the review dates
For every file you reviewed (changed or confirmed-current), set its reviewed_at in
knowledge/freshness.json to today's date.
4. Report
Summarize: which files were refreshed, what actually changed (old → new), and which were confirmed still current. The user reviews the git diff — this is a normal reviewed edit, not an autonomous rewrite.
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.
- 5d ago First seen · 46 lines · 14 tokens per session scan A 4575a63b8dfd
refresh-knowledge is a command published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 435 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
remember
Consolidate stashes + friction into project memory.
stash
Stash session context [name].
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
memory-forget
Command "memory-forget" from waittim/MemoryCustodian, covering memory-forget and review the preview, then apply its plan id.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.