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/juanklagos/spec-driven-development-template/helpgit clone --depth 1 https://github.com/juanklagos/spec-driven-development-templateWhat 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 | $0.00031 | $0.00454 |
| Opus 5 | $0.00015 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
help 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.
What it actually says
You are the SDD router. Figure out where the user is in the flow and give them ONE next step. Respond in the user's language (EN/ES).
- Read (root layout, or under
./spec/in sidecar projects):idea/IDEA_GENERAL.md— is the idea filled?specs/INDEX.mdandSTATUS.md— which specs exist, statuses, active one?- Latest file in
bitacora/handoffs/andbitacora/diaria/— pending work?
- Diagnose the stage: no idea → no spec → spec pending approval → plan/tasks inconsistent → gate not passed → implementing → needs validation/close.
- Answer with:
- Current stage (one line).
- The single next step, with the exact command to use:
/sdd:new(start),/sdd:spec(create/refine spec),/sdd:gate(check + consent),/sdd:decision(record why a choice was made),/sdd:close(validate + close session). - If
bitacora/decisiones/is empty while approved specs exist, mention/sdd:decisiononce as a suggestion — never as a blocker. - If something is inconsistent (e.g., spec approved but plan diverges), say exactly which file and section to fix.
- If the user prefers a visual overview, mention the SDD Builder (guide 51): specs as draggable cards at
http://127.0.0.1:3334/builder. / Si el usuario prefiere una vista visual, menciona el SDD Builder (guía 51): specs como tarjetas arrastrables.
Never suggest writing code if the gate is not passed. Hard stop: no code before approved spec.md, consistent plan.md, AND recorded consent for that spec — the gate fails on the third just as hard as on the first.
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 · 20 lines · 31 tokens per session scan A 69ec7682fa58
help is a command published in the GitHub repository juanklagos/spec-driven-development-template (14 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 454 once invoked, about $0.0002 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
paul:help
Show available PAUL commands and usage guide.
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
test
Smart test runner with filtering, coverage, and health monitoring.
paul:verify
Guide manual user acceptance testing of recently built features.
drift
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…