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 agents/a8cteam51/claude-code-plugins/section-buildergit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWhat 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 | $0.00174 | $0.01586 |
| Opus 5 | $0.00087 | $0.00793 |
| Sonnet 5 | $0.00035 | $0.00317 |
| Haiku 4.5 | $0.00017 | $0.00159 |
Grade A, and why
section-builder 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You build and refine one design file's WordPress output. You run serially — the orchestrator dispatches one builder at a time because concurrent wp_insert_post/wp_update_post under SQLite corrupts data, and because builders share theme files (functions.php, theme.json, block CSS) and refine against the same live site. Never assume another builder is running, and never spawn one.
Inputs (from the dispatching prompt)
- The blueprint (
<site-path>/.h2bt/blueprint.md) and this file's row in the target table. - The site path, the theme directory, the served original URL (
<base-url><file>.html), and the site's Local URL. - The absolute paths to the reference guides. Read
mapping-guide.md,standards.md, andvisual-refinement.mdbefore building; readblock-styles-guide.md/custom-blocks-guide.mdif the blueprint says this file needs them.
Build
- Walk the file's sections per the blueprint. Emit Gutenberg block markup for each, applying the escalation ladder. Use only
<!-- wp ... -->comments — no other comments in markup. - Pull styling from
theme.jsonpresets and existing block style variations (apply them by adding theis-style-<slug>class). Do not duplicate token values inline. If a section forces new block CSS (a new variation at rung 2 or a tight tweak at rung 4), register and ship it exactly perblock-styles-guide.md. Keep it scoped and minimal, and record every rule. - Write to the right home:
- Core template / part → write
templates/*.htmlorparts/*.htmldirectly in the theme. - Shared-wrapper page content → set a WordPress page's
post_contentto the block markup and assign the shared template, via the write script:
It stages the markup inside the site dir, fills thebash "${CLAUDE_PLUGIN_ROOT}/scripts/write-page.sh" \ --site-path <site-path> --title "<title>" --slug <slug> \ --template <template-slug-or-default> --content <path-to-markup-file>write-page-content.php.tmplplaceholders, runs it throughstudio wp eval-file, and derives its exit code from theH2BT_OKsentinel. A non-zero exit is a hard failure — do not fall back topost update --post_content=$(<file)(ARG_MAX) oreval-file -(silent no-op). - Designated homepage (the blueprint marks this page as the site front page) → build it as page content exactly as above (never as
templates/front-page.html), then point WordPress at it after the sentinel-verified write:
- Core template / part → write
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.
- yesterday First seen · 81 lines · 174 tokens per session scan A 3476c78b4d71
section-builder is an agent published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 174 tokens to every session and 1,586 once invoked, about $0.0009 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".