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/savenpx skills add gideondk/strata --skill savegit 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 | $0.00110 | $0.01216 |
| Opus 5 | $0.00055 | $0.00608 |
| Sonnet 5 | $0.00022 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
strata:save scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:save
Persist what just happened so the next session can pick up where this one
Left off. Lands in <vault>/<repo>/pr-context/<branch-slug>/<timestamp>--<initials>--<topic>.md.
Two modes
Direct (default)
User says "save this as " or you decide to save autonomously.
- Compose the note body in your reply.
- Write:
"${CLAUDE_PLUGIN_ROOT}/bin/strata" save \
--topic "<topic>" --kind session <<'STRATA_NOTE'
<note body>
STRATA_NOTE
Draft (interactive review)
User says "draft a save", "what would you save", or you're at the Stop-hook nudge and want help. Build a draft from real git state, then ask before writing.
- Snapshot the session:
"${CLAUDE_PLUGIN_ROOT}/bin/run-python.sh" -c \
"import sys; sys.path.insert(0, '${CLAUDE_PLUGIN_ROOT}/scripts'); \
import session_state; \
print(session_state.draft_note_body(session_state.snapshot()))"
The draft has four sections: What was done (from commits), In progress
(from uncommitted), Decided (placeholder), Left open (placeholder).
-
Present the draft. Offer:
- Accept — save with the suggested topic
- Edit — apply changes (or fill Decided/Left open from conversation), re-confirm
- Skip — abandon
-
On accept, pipe the final body through
strata savewith the topic from the draft.
Apply-draft (one-keystroke acceptance of a Stop-hook offer)
When the Stop hook stashes a pre-filled draft (it does this when the session crossed a signal threshold: 3+ commits, or 1+ commit with 3+ uncommitted files, or 8+ uncommitted files), the user can save it as-is with no further prompting:
"${CLAUDE_PLUGIN_ROOT}/bin/strata" save \
--apply-draft
The script reads ${PLUGIN_DATA}/pending-draft.json, writes it to the
current branch's pr-context/ folder, and clears the stash. Drafts older
than 24h are silently dropped (treat as no-op).
If the user wants to edit the draft first, snapshot it, present it, then
apply with the edited body (drop the stash via import draft_store; draft_store.clear_draft() after, or let it expire naturally).
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 · 128 lines · 110 tokens per session scan A 093b0b40f37f
strata:save is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 110 tokens to every session and 1,216 once invoked, about $0.0006 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…