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/mathiasbourgoin/rosterWrote 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/mathiasbourgoin/roster/kb-reindex)<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/kb-reindex"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/kb-reindex/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/mathiasbourgoin/roster/kb-reindex"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/kb-reindex.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 | $0.00020 | $0.01425 |
| Opus 5.5 | $0.00008 | $0.00570 |
| Sonnet 5.5 | $0.00004 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
kb-reindex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Reindex
You build or incrementally update a LanceDB vector index over the project's kb/ directory. This skill is opt-in — only run when search_index: true is set in the project's kb-agent tunable, or when explicitly invoked.
The index is a search cache. Markdown files remain the primary source of truth. The index is never committed to git.
Pre-conditions
# Opt-in flag lives in the installed kb-agent's frontmatter tunables (the file /roster-config
# edits) — NOT in .harness/harness.json, whose agents[].tunables carry no per-agent values.
AGENT_FILE=""
for f in .harness/agents/kb-agent.md .claude/agents/kb-agent.md .opencode/agents/kb-agent.md agents/management/kb-agent.md; do
[ -f "$f" ] && AGENT_FILE="$f" && break
done
grep -Eq '^[[:space:]]*search_index:[[:space:]]*true' "$AGENT_FILE" 2>/dev/null \
&& echo "search_index: enabled ($AGENT_FILE)" \
|| echo "search_index: disabled — enable via /roster-config (kb-agent › search_index), or proceed only on explicit user request"
# Check LanceDB is available (Python: pip install lancedb; JS: npm install @lancedb/lancedb)
[ -d kb ] && echo "KB present" || echo "KB absent — nothing to index"
If kb/ is absent: report and stop.
Read the configured embedding_mode before doing any network or credential check:
remote(default): use the configured embedding provider and model.disabled: reportsemantic index disabled; Markdown and deterministic claims remain availableand stop successfully without creating or changingkb/.index/.
Index availability is optional and MUST NOT affect claims validation, dependency closure, projection freshness, spec compliance, or any mandatory Roster gate. Never silently replace a disabled or failed embedding provider with agent-generated similarity judgments.
Migration warning: if any KB file lacks schema-version: 2 in frontmatter, emit:
⚠️ Some KB files have not been migrated to schema v2. Run
/kb-migratefirst for best results. Continuing anyway — legacy files will be indexed with status inferred from old values.
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.
- 1mo ago First seen · 127 lines · 20 tokens per session scan A 56691164441b
kb-reindex is a command published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,425 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-07.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.