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/correctnpx skills add gideondk/strata --skill correctgit 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 | $0.00160 | $0.00979 |
| Opus 5 | $0.00080 | $0.00490 |
| Sonnet 5 | $0.00032 | $0.00196 |
| Haiku 4.5 | $0.00016 | $0.00098 |
Grade A, and why
strata:correct scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:correct
The unified correction surface. One skill, three operations distinguished by intent and flags.
Decide the operation
| Situation | Path |
|---|---|
| One paragraph is wrong, note overall still useful | edit (default) |
| User corrects something Claude proposed in conversation | learn-from (see below) |
| Whole note no longer current, keep history visible | invalidate |
| ADR replaced by new decision | use /strata:decide --supersedes |
| Note must disappear (PHI, secrets) | use /strata:forget |
Edit (default)
Replace body
cat <<'EOF' | "${CLAUDE_PLUGIN_ROOT}/bin/strata" correct \
domain/order-aggregate.md \
--reason "OrderPriced now emitted before OrderConfirmed, not after."
# Order Aggregate
<new content here>
EOF
Update one field
"${CLAUDE_PLUGIN_ROOT}/bin/strata" correct \
domain/order-aggregate.md \
--set status=stable \
--reason "Adopted in production after two-week rollout."
--set is repeatable. --reason strongly recommended, appears in the
corrections: audit list.
Invalidate
The note stays readable but drops out of default search. Required --reason,
optional --replaced-by:
"${CLAUDE_PLUGIN_ROOT}/bin/strata" invalidate \
domain/old-aggregate-pattern.md \
--reason "Aggregate split into Order + Payment in 2026-05-24 refactor." \
--replaced-by "domain/order-aggregate.md"
Correcting something Claude proposed (from a conversation)
When the user corrects an idea Claude just gave ("no, X is actually Y", "that's wrong because Z", "we don't do it that way", "you got it backwards"), that's signal worth keeping. Flow:
- Recall the topic —
recall(query="<topic>", layer=1). - One match → correct that note (above), adding
--set correction_source=claude-sessionso the audit trail shows the correction came from a session, not a manual edit. Several matches → ask which one. No match → the vault didn't know this yet; create the right note instead: a chosen approach →/strata:decide, a vocabulary/invariant →/strata:domain, a newly-surfaced contested point →/strata:propose --status contested. Include in the body: "Claude proposed: ; actual: " so future readers see the genesis. - Confirm in one line with the path edited/created.
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 · 97 lines · 160 tokens per session scan A d42c4f0e328e
strata:correct is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 160 tokens to every session and 979 once invoked, about $0.0008 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…