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 commands/intentdriven/abcd/sitegit clone --depth 1 https://github.com/intentdriven/abcdWhat 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 | $0.00074 | $0.02024 |
| Opus 5 | $0.00037 | $0.01012 |
| Sonnet 5 | $0.00015 | $0.00405 |
| Haiku 4.5 | $0.00007 | $0.00202 |
Grade A, and why
site scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:site the website as a surface of the record
A project's website drifts from the project. Copy is written for the site,
lives only there, and slowly stops being true; the record that says what the
project actually decided stays invisible in frontmatter nobody reads. This
command renders a site that cannot drift, because it contains no words of its
own: every sentence is a span of a file in this repository, selected by path and
heading through .abcd/site.json.
Bare — what this repo has declared
"${CLAUDE_PLUGIN_ROOT}/abcd" site --json
emits { "manifest": …, "ui_strings": …, "baseline": …, "out_dir": … }:
manifest— whether.abcd/site.jsonis present. Absent means this repo declares no composition, and there is nothing to render.chapters— how many chapters the manifest composes the landing page from.issue_ledger— whether the working-tier issue ledger is published. It is an explicit per-repo opt-in; the default renders the durable record only.ui_strings— whether the interface-string allowlist the manifest names is present. It is the complete list of words the generator may add.baselineandbaseline_entries— the committed unresolved-reference ratchet and its size.version,commit— what a render would stamp the footer with.out_dir,out_exists,out_files— where a render writes, and what is there now.
Report the declared inputs first, then the output directory's state. It writes
nothing and exits 0 whatever it finds.
build — render the site
"${CLAUDE_PLUGIN_ROOT}/abcd" site build --out site
reads exactly this set — .abcd/site.json, site-src/ui.json,
.abcd/record-lint.json (where the record stores are), the record under
.abcd/development/ and the opted-in issue ledger, git history,
CHANGELOG.md, the composed pages and assets under docs/, the static inputs
site-src/{site.css,site.js,record.js,redirects,headers} and the served
site-src/install.sh.tmpl, the credit sources CONTRIBUTING.md and
ACKNOWLEDGEMENTS.md (and the existence of SECURITY.md and CITATION.cff
for the footer), .abcd/site-baseline.json (the ratchet the health block
counts against), and .claude-plugin/plugin.json (the forge URL, licence and
author the links and footer use) — and writes the landing page, the record
export, the redirect and header maps, the stylesheet, the two scripts, the
install.sh, and every referenced raster into the output directory, and
nowhere else. It reaches no network. The default output directory is site,
which the repository does not track.
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 · 152 lines · 74 tokens per session scan A 20bc8120ff28
site is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 2,024 once invoked, about $0.0004 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 commands, from other repositories
legal
Primary entry point for all BetterCallClaude requests — classifies intent, resolves jurisdiction (via swiss-legal-research), runs inline briefing for complexity 4–6, activates full briefing session when complexity ≥ 7 (via legal-intake skill), and routes to specialist agents or workflow pipelines. Invoked explicitly…
briefing
Structured pre-execution briefing session -- collects case context through specialist panel, builds execution plan, supports resume and depth control.
help
Show complete BetterCallClaude command reference, available agents, skills, and usage examples.
legal-5step
Execute the BetterCallClaude 5-step Swiss legal framework: intake → research → strategy → adversarial → draft. A complete end-to-end pipeline for any Swiss legal matter, from document analysis through final legal output.
legal-loop
Iterate a worker-evaluator cycle against a Goal Record until the success condition is met or a stop limit is reached. The evaluator (a different agent than the worker) judges each iteration using MCP verification tools. Produces an auditable verdict trail and a final MET / NOT MET status.
workflow
Define and execute multi-agent legal workflows -- due diligence, litigation prep, contract lifecycle, real estate closing.