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-check-driftgit 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-check-drift)<a href="https://agentmods.dev/skills/olegvg/olegvg-skills/kb-check-drift"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-check-drift/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-check-drift"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-check-drift.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 | $0.00069 | $0.01468 |
| Opus 5 | $0.00034 | $0.00734 |
| Sonnet 5 | $0.00014 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
kb-check-drift 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-check-drift — Surface Refresh Candidates
When to use
User wants to know whether the KB is stale without committing to a rewrite. Run this before a query to decide whether to trust the KB, or periodically to spot drift.
Read-only. This skill NEVER modifies .kb/ content, summaries, indexes, or .kb-state.json. If changes are warranted, emit a list of refresh commands for the user to run.
The one exception: when invoked by kb-maintain or with --write-artifact, the skill writes an opt-in .kb/.drift-report.json so the downstream kb-refresh can reuse the diff/grep work. The artifact is ephemeral and recomputable — see references/drift-report-artifact.md.
Input
--write-artifact(optional) — write.kb/.drift-report.jsonafter computing the report. Implied when invoked bykb-maintain.
Workflow
1. Read state
Open .kb/.kb-state.json. Extract last_linted_sha and last_linted_at.
If missing: report "no KB state — build or refresh has never run". Do not proceed.
If last_linted_sha == "no-git": report that drift check requires git. Stop.
2. Log the delta
Run:
git -C <corpus-root> log --stat <last_linted_sha>..HEAD
git -C <corpus-root> diff --name-status <last_linted_sha>..HEAD
Capture the list of changed files, rename/copy stats, deletions, additions, and commit messages.
3. Apply the heuristic
The heuristic is a checklist. Tune it by editing this file. The default checklist:
- New files above threshold — if a single directory or area saw ≥5 new files since last refresh, flag that area.
- File renames or moves — any rename under a directory referenced in
.kb/indexes/is a flag. Index references are stale by definition. - Changes to files referenced by existing indexes — grep
.kb/indexes/for paths; if any flagged path appears, the index entry is suspect. - Changes to files referenced by existing summaries — grep
.kb/summaries/for paths; if any flagged path appears, the summary is suspect. - New top-level directory — may mean a new area needs an index.
- Migration / schema files (e.g.
migrations/**,*.sql,schema.*) — semantic shifts likely; any area touching data is suspect. - Deleted files referenced in
.kb/— hard flag. The KB points at something that no longer exists. - Completed plan with no decision record — if a plan file under
docs/plans/(or similar) has a sibling checklist with all items ticked, and no matching file exists in.kb/decisions/(match by slug), recommendkb-record-decision <plan-path>. Soft flag — not every plan yields a durable decision.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 109 lines · 69 tokens per session scan A 656b6b61b58e
kb-check-drift is a skill published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,468 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-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.
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.