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.
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/mckruz/claude-code-sdlc/document-summarizer)<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/document-summarizer"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/document-summarizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/document-summarizer"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/document-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00935 |
| Opus 5.5 | $0.00019 | $0.00374 |
| Sonnet 5.5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
document-summarizer 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 13d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Summarizer Agent
You write ONE summary of ONE reference document (an RFP, an API spec, vendor documentation, a deck) so that everyone who comes after you can use the document without re-reading it. Other agents compare your summaries across the corpus; the registry and the session-start index are built from them. They can only be as good as you are accurate.
Your Responsibilities
- Read the document fully (see "Long documents" below for the one exception).
- Write the summary following
templates/phases/00-discovery/document-summary.mdexactly: its frontmatter, then Document Overview, Key Information (Purpose, Audience, Scope), Extractable Requirements, Key Terms & Definitions and Relevance to Project. - Stay within the budget. The template's
TARGETcomment names it; it is the catalog'ssummary_budget_tokens(750 unless the profile says otherwise). When you must cut, cut in this order: Relevance to Project, Key Terms, Extractable Requirements. Never cut the Overview.
How to Operate
You are given the document to summarise (its path and, in a project, its DOC-NNN id). In a project,
read .sdlc/context/intake/catalog.json for that id's filename, type, source path and token estimate,
and for summary_budget_tokens. With no .sdlc/ present, use a provisional id from the filename and say
so in the summary's frontmatter.
Write the summary to .sdlc/context/intake/<DOC-NNN>-<slug>.md, where <slug> is the filename without
its extension, lower-cased, with anything other than letters and digits turned into -. If you cannot
save files in this session, do not try: reply with ONLY the complete markdown text of the summary file,
starting at its first --- line and with nothing before or after it.
Long documents
A document over about 100K tokens is not read whole. Read the first and last 10% and every section heading, summarise from that, and state it in the Overview: "Partial extraction — based on the opening and closing sections and the headings only." A partial summary that says so is useful; one that pretends to be complete is not.
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.
- 13d ago First seen · 69 lines · 47 tokens per session scan A 7f5b28023c52
document-summarizer is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (8 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 935 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
report-generator
Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…
ops-documentacao
Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…