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/olegvg/olegvg-skillsWrote 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/olegvg/olegvg-skills/kb-refresh)<a href="https://agentmods.dev/commands/olegvg/olegvg-skills/kb-refresh"><img src="https://agentmods.dev/badge/commands/olegvg/olegvg-skills/kb-refresh/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/olegvg/olegvg-skills/kb-refresh"><img src="https://agentmods.dev/badge/commands/olegvg/olegvg-skills/kb-refresh.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 | $0.00013 | $0.00234 |
| Opus 5 | $0.00006 | $0.00117 |
| Sonnet 5 | $0.00003 | $0.00047 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
kb-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 9d 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
Invoke the kb-refresh skill with the path(s) in $ARGUMENTS. Multiple paths may be passed in a single call (preferred over N sequential calls) — the skill batches the diff and advances state once.
If $ARGUMENTS is empty:
- Do not infer scope from
git status, the working tree, or "everything since the watermark". - Do not default to the whole corpus, even in auto / non-interactive modes — that path leads straight to the scope-budget failure documented in the skill.
- Invoke
kb-check-driftfirst (the skill's step 0 does this) so the user can pick refresh candidates from a real report instead of letting the agent guess.
When the user supplies the path(s), the skill enforces a scope budget after the diff — if the change is too large for one refresh pass, it will stop and ask the user to narrow scope or split the work across multiple invocations / areas.
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.
- 9d ago First seen · 15 lines · 13 tokens per session scan A 7537179c2225
kb-refresh is a command published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 234 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
pane
Open the Engram graph pane — make sure the machine core is running and share the URL.
digest
Digest this project into Engram — an explicit, one-time ingestion of the current working tree into typed memory nodes.
gaai-ask
Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).
gaai-bootstrap
Initialize or refresh project context via Bootstrap Agent.
tl-export
Export thoughtline memories to a markdown file the user can review or commit.
tl-recent
Show the most recent thoughtline memories for the active project.