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/dinhnguyenngoc/spec-driven-claude-code/export-docsgit clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-codeWrote 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/commands/dinhnguyenngoc/spec-driven-claude-code/export-docs)<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/export-docs"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/export-docs.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.04759 |
| Opus 5 | $0.00013 | $0.02380 |
| Sonnet 5 | $0.00005 | $0.00952 |
| Haiku 4.5 | $0.00003 | $0.00476 |
Grade A, and why
export-docs 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 4d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/export-docs — Company-Standard Document Export
"The artifacts are the source of truth; the company doc is a rendering."
Purpose
Render the kit's SDLC artifacts (specs/, architecture/, security/, reports/, docs/…) into company-standard documents (e.g. a corporate PRD/SDD template) without duplicating authorship. The export is fill-only: every filled section traces to a kit artifact; anything the artifacts cannot answer becomes an explicit N/A — <reason> or a [NEEDS <role/command>] handoff marker — never invented content.
Content changes never happen here. A gap discovered during export (missing goals, missing threat model…) routes back to /spec / /arch / /secure as a new change-set, then re-export. Gate 1/2 stay the only places where requirements/design change; this command only re-renders.
Usage
| How to invoke | Result |
|---|---|
/export-docs prd |
Compile the PRD target per the manifest → exports/PRD.md + exports/TRACE_MAP.md |
/export-docs sdd |
Compile the SDD target → exports/SDD.md (+ TRACE_MAP refresh) |
/export-docs prd --draft |
Export although specs/SPEC.md is still Draft — line 1 of the output carries a **DRAFT — not yet Gate-1 signed-off** watermark (phrased per the artifact's Output Language) |
| Re-run any target | Refresh: regenerate + print a per-section diff summary vs the previous export; every previously issued ID stays stable (§ID stability) |
Workspace Mode: if the session root declares
Mode: workspace→ resolve the target repo perCLAUDE.md§Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate. A target declaringScope: systeminstead runs at the workspace ROOT: sources =specs/system/+architecture/system/(+ per-repo artifacts via the registry when a row cites them); output = the rootexports/; the workspace disk-check exception covers it.
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.
- 4d ago First seen · 210 lines · 26 tokens per session scan A 4d077bcc7402
export-docs is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 4,759 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
codebase-knowledge
Present a structured knowledge document for this codebase — architecture overview, module map, public API surfaces, and patterns. Knowledge-presentation only (no defect ranking). Use /swe-workbench:audit-codebase for defect sweeps; /swe-workbench:document for generating new prose docs.
document
Generate or update documentation (README, ADR, ARCHITECTURE, inline comments) via the tech-writer subagent.
speckit.harness.report
Synthesize curated evidence and verification records into the feature's research.md with a coverage table.
docs-helpers
Open ArchiPy helpers docs (utils, decorators, interceptors).
speclan-engineering:hlrd
Interactive HLRD (High-Level Requirements Document) import — transforms an unstructured requirements document into speclan vision, mission, goals, features, and requirements through a multi-phase wizard with AskUserQuestion-driven clarifications.
journey-map
Document a user journey from screen references and a user story input. Produces a journey spec doc matching the JOURNEYSPEC.md template with outcome, screen flow, components consumed, critical states, accessibility, security, and performance sections. Use when mapping a user flow across multiple screens. Do not use…