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/initnpx skills add gideondk/strata --skill initgit clone --depth 1 https://github.com/gideondk/strataWhat 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 | $0.00089 | $0.01013 |
| Opus 5 | $0.00044 | $0.00507 |
| Sonnet 5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
strata:init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:init
Three-step onboarding. Always step 1; step 2 and 3 are user-chosen.
Step 1 · create the vault namespace
Always do this. Idempotent.
"${CLAUDE_PLUGIN_ROOT}/bin/strata" init
Creates <vault>/<repo>/{decisions,domain,lessons,procedural,propositions,pr-context}/
Plus INDEX.md. Vault path defaults to ~/StrataVault, overridable
via STRATA_VAULT_PATH or plugin userConfig.vault_path.
init-memory.py also runs an inline venv health check at the end —
imports every required package and reports any missing required or
Optional deps. The bootstrap-venv.sh wrapper auto-installs from
requirements.txt on first run, so this is usually green, but it
Makes the state legible to the user before they invoke their first
Save / decide / recall.
Show the user the resulting layout in one line:
✓ Strata initialised at ~/StrataVault/<repo>/
scopes: decisions/ domain/ lessons/ procedural/ propositions/ pr-context/
Step 2 · ask about Graphify
Graphify is a separate tool that builds a code structure graph from
your repo. With it, Strata unlocks code_map, drift detection,
aDR↔commit linkage, hot-file ranking, and verified code_refs: on
Notes. Without it, Strata still works. Minus code-graph awareness.
Ask the user (yes / no / later):
Want to install Graphify now? It unlocks code-graph features (
code_map, drift detection, ADR verification). Separate binary, runs locally. Skip if you're just trying Strata out.
If yes
Show the install command. Don't run it yourself. Paths vary, they may want sudo, they may already have it:
# macOS via Homebrew
brew install graphifylabs/tap/graphify
# Or use the installer at https://graphifylabs.ai/install
Then offer to build the first graph:
"${CLAUDE_PLUGIN_ROOT}/bin/strata" graphify
If no / later
Acknowledge briefly. Mention /strata:graphify runs the build
Whenever they're ready. Continue to step 3.
Step 3 · ask about bootstrap
If the repo has an existing .planning/, docs/, or similar
directory of markdown that predates Strata, the bootstrap pipeline
Can migrate that content into the vault. Cross-references claims
Against git history + the code graph; classifies into ADR / domain /
Lesson; writes notes with provenance.
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 · 123 lines · 89 tokens per session scan A 9b28e0021d56
strata:init is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 89 tokens to every session and 1,013 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…
save-to-favorites
The single complete Pickoo workflow for new Xiaohongshu, WeChat, Douyin, Bilibili, Xiaoyuzhou, podcast, music, article/blog, or general web links. Use for 收藏、保存、收录、抓取、归档、拆解、分析、OCR、ASR or 完整处理 from Codex, WorkBuddy, Hermes, Claude, or Claudian. It owns intake and the complete downstream workflow; obsolete standalone…
asset-review-agent
Independently review source-extracted quote, viewpoint, hook, and structure candidates. Image and shot assets are outside automatic review and enter only after explicit user interaction.
phase-orchestrator
Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes…
answer-processing
Use whenever the user uploads a hand-written or scanned answer PDF to be graded against a reference solution. Converts answer PDFs in answers/.pdf to markdown in answers/converted/.md using the pdf skill (OCR as needed), then performs strategy-based grading against converted/solutions/.md or quizzes/answers.md.…
course-builder
Use whenever the user wants to ingest a new course's materials (lecture notes, textbook chapters, HW problems, HW solutions) and build the course-specific knowledge base — patterns.md (recurring solution techniques), coverage.md (HW-to-section map with 🔥 exam tiers + ⚠weak flags), and summary.md (topic tree). Invoked…