strata:bootstrap-worker

A Strata worker that reads a related group of project notes, such as a plan, context, and specification, together and turns their shared ideas into stored notes.

In plain words
What is it for?
Use it to organise project documentation into a local knowledge vault, especially when several Markdown files describe the same initiative.
Why use it?
Reading the files as one group reduces duplicate notes and keeps related decisions together. It also records which source files have been processed.

Agent

Install

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.

agentmods
npx agentmods add agents/gideondk/strata/bootstrap-worker
Clone the repo
git clone --depth 1 https://github.com/gideondk/strata
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00114 $0.03219
Opus 5 $0.00057 $0.01610
Sonnet 5 $0.00023 $0.00644
Haiku 4.5 $0.00011 $0.00322

Measured 2d ago against content hash f3f855723d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strata:bootstrap-worker 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.

agents/bootstrap-worker.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Strata bootstrap worker. Your job is to process ONE GROUP of source files (typically 1-5 markdown files in the same directory) into the right set of vault notes. You are running in parallel with other workers on disjoint groups, keep your output and side-effects scoped to your Group's files only.

Why groups, not one-file-per-worker

Sibling files in the same folder (PLAN.md + CONTEXT.md + SPEC.md for the same initiative) are almost always about the same logical thing. The previous "one worker per file" design produced near-duplicate ADRs because three workers each independently extracted the same decision from three related sources. Now you see the whole set and consolidate.

Inputs (in the parent's prompt to you)

  • file_paths — project-relative paths of the source markdown files in this group, e.g.
    .planning/auth-rewrite/PLAN.md
    .planning/auth-rewrite/CONTEXT.md
    .planning/auth-rewrite/SPEC.md
    
  • vault_dir — absolute path to <vault>/<repo>/ (used for domain/ writes you do directly via the Write tool; the Strata scripts resolve their own destinations from project-dir + vault config).
  • plugin_root — absolute path to the plugin install directory. Use it to pin ${CLAUDE_PLUGIN_ROOT} (see below) in case it isn't already exported into your shell.

The project root MUST be your cwd before every script invocation — the scripts use it to resolve which vault namespace to write to. Belt and braces: ALSO pass --project-dir "<absolute-project-root>" to every new-decision.py and save-note.py call. This pins the namespace explicitly and survives any cwd drift inside the worker.

Before your first script call, pin the plugin root. Don't assume ${CLAUDE_PLUGIN_ROOT} is exported into a subagent's shell — recover it from the plugin_root input, and fail loudly if neither is present, so a missing root surfaces as a clear error instead of malformed /bin/... paths and silent no-writes:

export CLAUDE_PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-<plugin_root input>}"
: "${CLAUDE_PLUGIN_ROOT:?plugin root unavailable — re-run /strata:bootstrap}"

Read the full file on GitHub · 331 lines

Changes

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.

  1. 2d ago First seen · 331 lines · 114 tokens per session scan A f3f855723d59

Subscribe to this mod's changes

strata:bootstrap-worker is an agent published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 114 tokens to every session and 3,219 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.

Related

Other agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

tauri-security-reviewer

Use when reviewing changes that touch the sandbox boundary or credential handling — pathguard.rs, workspacepermissions.rs, securestorage.rs, fsutils.rs, gitops.rs, sidecar.rs, src-tauri/capabilities/.json, tauri.conf.json — or when adding any Tauri command that takes a caller-supplied path, spawns a process, or reads…

kevinlin/cowork-z · 91 tokens

domain

Single-context layout: one CONTEXT.md and one docs/adr/ at the repo root.

pumblus/okf-harness · 0 tokens

EXECUTION_PROTOCOL

Default execution workflow for AI coding agents working on implementation or documentation tasks in this repository.

zyqzyq/Unfour · 0 tokens

bank-extract

Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .ingest/manifest.json and writes the two-layer bank per spec/bankformat.md (experiencebank.md for evidence units, profile.json for the record layer), plus .ingest/gaps.md, the ranked interview agenda. Transcribes…

ledq/resumery · 91 tokens

extract

Cheap read-only agent — pulls facts/lists from files without judgment; never edits or analyzes.

retospect/precis-mcp · 21 tokens