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/proposenpx skills add gideondk/strata --skill proposegit 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 | $0.00118 | $0.01459 |
| Opus 5 | $0.00059 | $0.00730 |
| Sonnet 5 | $0.00024 | $0.00292 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
strata:propose 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:propose
The "open question" scope. Closes the gap between what we know (domain), what we've chosen (decisions), what we did (pr-context), and what we did wrong (lessons), with a fourth: what we're still Figuring out.
When to use
| Situation | Skill |
|---|---|
| Open question, multiple positions, no choice yet | strata:propose |
| Chosen option with reasoning | strata:decide |
| Stable concept / vocabulary | strata:domain |
| Retrospective fact | strata:save --scope lessons |
| In-flight branch work | strata:save |
A proposition is explicitly time-bounded. It exists to be resolved. A proposition that never gets settled or refuted is itself a signal.
How
Recall before you open it
Before creating a proposition, call recall to check it isn't already
tracked. Two agents opening the same open question — or re-litigating one
that's already decided — is the failure this prevents:
recall(query="<the question, in your words>", scope="propositions", layer=1)
Then run a second pass with scope="decisions". Adjudicate:
- existing open proposition → add a position to it (below), don't fork.
- already settled or decided → tell the user and point at the note; write nothing.
- genuinely new → create it.
Create
cat <<'EOF' | "${CLAUDE_PLUGIN_ROOT}/bin/strata" propose \
--title "Should we move to Postgres for tenant data?"
# Should we move to Postgres for tenant data?
## What we're trying to figure out
<context — why this is open>
## Positions on the table
- Stay on SQLite: <reasons>
- Move to Postgres: <reasons>
## What evidence would settle this
- <what we'd need to know>
EOF
Default status is open. Pass --status contested if multiple positions
are actively defended, or --status converging if one is winning.
Add a position (the debate log)
When someone weighs in on an open proposition, append a position — don't rewrite the note. Each entry is attributed, dated, and append-only:
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.
- 3d ago First seen · 147 lines · 118 tokens per session scan A f10e1e3b86ff
strata:propose is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 118 tokens to every session and 1,459 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…