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/bootstrapnpx skills add gideondk/strata --skill bootstrapgit 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 | $0.00109 | $0.01647 |
| Opus 5 | $0.00055 | $0.00823 |
| Sonnet 5 | $0.00022 | $0.00329 |
| Haiku 4.5 | $0.00011 | $0.00165 |
Grade A, and why
strata:bootstrap 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strata:bootstrap
Onboarding pass. Walk existing docs, dispatch each one to a worker Subagent, aggregate the results.
Posture: act, don't narrate
- No upfront questions about scope unless the candidate count is > 50.
- No tables, no recommendations, no "two-step plan" prose before starting work.
- Source file content stays out of your context — that's the whole point of the workers. You see only the scan listing and the one-line worker summaries.
- Final summary: one line plus counts. The user can
/strata:reviewfor detail.
Workflow
1. Scan
bootstrap_scan(unprocessed=true, bucket="fresh", verify=true,
min_freshness=0.6, max_group_size=12)
Default pass: fresh docs only (<90d), claims verified, freshness ≥ 60%,
dense parent dirs split into sub-groups of at most 12 files
(by date prefix when filenames are dated). For a wider net, drop
min_freshness to 0.4, or omit bucket so aging + old appear too.
max_group_size is what stops dense planning folders (a docs/plans/
with 40+ unrelated initiatives) from collapsing into 3-6 consolidated
Notes. Pass max_group_size=12 for typical mixed-initiative folders;
Omit it for folders where siblings genuinely describe one thing.
If after filtering the candidate count is > 50, ask the user once to Narrow scope (e.g. by directory). Otherwise proceed.
2. Get the vault dir
memory_status()
Note the vault_dir path printed in the response. You'll pass it to
Each worker.
3. Dispatch by parent-dir GROUP, not by single file
The scan's JSON output (when --json is on) includes a
dispatch_groups map keyed by parent directory. Sibling files in
the same folder (e.g. .planning/auth-rewrite/PLAN.md +
.../CONTEXT.md + .../SPEC.md) almost always describe the same
Initiative, dispatch them to ONE worker that handles the set together
and writes one consolidated note, not three near-duplicates. (Previous
"one worker per file" dispatch produced the duplicate ADRs we saw on
the earliest bootstrap runs.)
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 · 168 lines · 109 tokens per session scan A c7693a3c59e5
strata:bootstrap is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 109 tokens to every session and 1,647 once invoked, about $0.0005 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…