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 olegvg/olegvg-skills --skill kb-querygit 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/skills/olegvg/olegvg-skills/kb-query)<a href="https://agentmods.dev/skills/olegvg/olegvg-skills/kb-query"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-query/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/olegvg/olegvg-skills/kb-query"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-query.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 | $0.00064 | $0.01016 |
| Opus 5 | $0.00032 | $0.00508 |
| Sonnet 5 | $0.00013 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
kb-query 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 12d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-query — Answer via Progressive Disclosure
When to use
User asks a question about a corpus that has a .kb/ directory. The knowledge base exists — you're reading it, not building it.
If .kb/ does not exist, suggest /kb-build and stop.
Input
- Question — natural language, from the user.
Workflow (strict order)
1. Read _root.md first
Open .kb/indexes/_root.md. Always. No exceptions on first access to the KB.
This is the indexes-first rule. It's cheap (≤300 tokens) and orients you correctly in one hop. Skipping it to "save time" costs more time when you pick the wrong summaries.
2. Pick 1–3 area indexes
Based on _root.md, identify which areas are relevant to the question. Read those area indexes (.kb/indexes/<area>.md).
Typical count: 1 for focused questions, 2–3 for questions that cross domains. More than 3 means either the question is too broad or the areas are over-segmented.
3. Descend to summaries
From the area indexes, pick the specific leaf summaries to read. Read them.
4. Follow warm references freely
Once inside a summary, you may follow direct references to other summaries without returning to the index level. This relaxation is intentional — see docs/navigation-rules.md. The indexes earn their keep on cold start; warm references are cheap.
4a. Surface decisions for the current summary
After reading a summary, also check whether any decision records reference it. Decisions live in .kb/decisions/<YYYY-MM-slug>.md; each record's ## Affected areas block names the summaries it shapes. The lookup is one grep:
grep -l "<path-to-current-summary>" .kb/decisions/
Read whichever records the grep returns. Do not look for a ## Key decisions section inside the summary — the linkage lives in the decision record, not in the summary. Decisions are immutable history; summaries describe the present.
For questions of the form "how does X work now, and why was it built that way?" — read the summary for X, then the decisions returned by the grep above. Both halves of the answer live along one navigation path.
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.
- 12d ago First seen · 85 lines · 64 tokens per session scan A ad6f8e2e9a58
kb-query is a skill published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,016 once invoked, about $0.0003 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 skills, from other repositories
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
memory-archive-superseded
Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.
memory-reconcile
Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.