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 agentmods add skills/gideondk/strata/reviewnpx skills add gideondk/strata --skill reviewgit clone --depth 1 https://github.com/gideondk/strataWrote 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/gideondk/strata/review)<a href="https://agentmods.dev/skills/gideondk/strata/review"><img src="https://agentmods.dev/badge/skills/gideondk/strata/review.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.00432 |
| Opus 5 | $0.00039 | $0.00216 |
| Sonnet 5 | $0.00016 | $0.00086 |
| Haiku 4.5 | $0.00008 | $0.00043 |
Grade A, and why
strata:review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
strata:review
ADR practices die in two years because nobody comes back to maintain them. This skill is the antidote: a monthly (or whenever) pass that surfaces the Notes that need attention.
Read-only by design, flags issues, never auto-fixes.
When to run
- Monthly, as a recurring habit. 30 minutes of cleanup.
- Before a release, to leave a clean snapshot in the vault.
- When the vault search starts feeling noisy.
How
"${CLAUDE_PLUGIN_ROOT}/bin/strata" review
# Tune the staleness thresholds
"${CLAUDE_PLUGIN_ROOT}/bin/strata" review \
--stale-days 7 --pr-stale-days 14
What it surfaces
| Signal | What to do |
|---|---|
| Stale-proposed ADRs | Either accept, reject, or /strata:decide --supersedes |
| Orphan domain notes | Add wikilinks, or merge into a neighbour |
| Missing frontmatter | Add status: (decisions/lessons) so the index can find them |
| Unresolved wikilinks | Typo — fix the target or create the missing note |
| Stale PR-context dirs | Run /strata:archive if the branch is merged |
What backs this
review.py reads these signals from internal db helpers — stale_decisions
and orphan_notes. They aren't callable MCP tools; /strata:review is how you
surface them. For ad-hoc triage outside the full report, use the recall MCP
tool.
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.
- 5d ago First seen · 46 lines · 79 tokens per session scan A f763a8bc346d
strata:review is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 79 tokens to every session and 432 once invoked, about $0.0004 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
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
mneme-search
Use when the user asks a factual question whose answer might live in the vault. Invokes mnemesearch. Production mnemesearch is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.
mneme-prime
Use when the user starts a new task that may have prior vault context worth surfacing. Invokes the mnemeprime MCP tool to build a token-budgeted preamble of recent sessions and topic matches.
memory-forest
Build, validate, index, and query a private local Memory Forest with provenance-aware layers, pointer-first search, and validated root-first retrieval. Use when creating a new forest, checking an existing forest's structure, building its local SQLite index, or retrieving bounded memory trails without exposing full…
brain
Orient in the user's big-brain second brain and work brain-aware for the rest of the session. Use when the user types /brain, or asks "what am I working on", "what's on my plate", "catch me up", "what's overdue", or at the start of a session about ongoing work. Loads the vault overview, reports it in one screen, and…