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-migrate)<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/kb-migrate"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/kb-migrate/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-migrate"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/kb-migrate.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 | $0.00032 | $0.01297 |
| Opus 5 | $0.00016 | $0.00648 |
| Sonnet 5 | $0.00006 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
kb-migrate 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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Migrate
You perform a structured, human-gated migration of an existing project KB to the current roster schema. Five sequential phases: audit, cleanup, reorg, frontmatter migration, verify.
Idempotency guarantee: running this skill twice on the same KB produces no additional changes. Files with schema-version: 2 in frontmatter are skipped in Phase D.
Pre-conditions
[ -d kb ] && echo "KB present" || echo "KB absent — nothing to migrate"
If no kb/ directory: report "No KB found. Run /roster-init to bootstrap one." and stop.
Steps
Phase A — Audit
Run all available auditors on the existing KB:
- Run
ambiguity-auditoron all KB files. Collect: undefined terms, vague quantifiers, contradictions. - Run
spec-compliance-auditorif codebase is present. Collect: spec vs code divergences. - Run
check-kb-links:node scripts/check-kb-links.js(ornpm run check:kb-links). Collect: broken relative links.
Produce a Findings Summary:
## Audit Findings
### Broken links (N)
- <file>: [link] → <target> (not found)
### Ambiguity issues (N)
- <file>: <issue>
### Spec compliance issues (N)
- <file>: <issue>
### Migration candidates (files without schema-version: 2)
- <file>: status=<old-value>
Present findings to the human. Gate: proceed to Phase B only after human acknowledges.
Phase B — Cleanup
For each finding from Phase A:
- Broken link: propose the correct target (search for similar filenames) or mark as "file missing — create or remove link". Human approves per item. Apply approved fixes.
- Ambiguity issue: propose precise language replacement. Human approves. Apply.
- Spec compliance: present the divergence, ask: "Fix code or amend spec?" Do not resolve unilaterally.
After all items are resolved or explicitly deferred:
## Cleanup Summary
Applied: N fixes
Deferred: M items (listed)
Gate: human confirms cleanup is complete.
Phase C — Reorg
Compare current KB structure against the schema tier (minimal/standard/large) appropriate for the project size:
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.
- 2d ago First seen · 149 lines · 32 tokens per session scan A 43ca30eaf42a
kb-migrate is a command published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 1,297 once invoked, about $0.0002 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 2026-09-07.
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.
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.
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.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.