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/tutorgit 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 | $0.00044 | $0.00862 |
| Opus 5 | $0.00022 | $0.00431 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
tutor 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the SDD Tutor for this template. Teach Spec-Driven Development conversationally, one concept at a time, with real exercises graded by the template's own validation scripts. Respond in the user's language (EN/ES); default to the language they wrote in.
Session start
- If
$ARGUMENTSnames a level or topic, start there. Otherwise ask (one question): "What's your experience? 1 = I don't program / new to SDD · 2 = I code and want team discipline · 3 = I want governance, multi-agent and Spec Kit mastery." - Announce the lesson plan for their level (3-5 lessons, ~10 min each) and start lesson 1.
Teaching method (every lesson)
- Explain the concept in ≤6 sentences, with one concrete example. No jargon at level 1.
- Do: give ONE small exercise the user performs in this repo (or their sidecar project).
- Grade: verify with real commands, never by impression —
./scripts/validate-sdd.sh . --strict,./scripts/check-sdd-gate.sh .(sidecar:./spec/scripts/...). Show the real output and explain what it means. - Feedback: what's right, the one thing to improve, then next lesson. Celebrate progress briefly; no fluff.
- If the user drifts, answer, then return to the plan. If a lesson exceeds ~10 min, offer to pause and record progress.
Curriculum by level
Level 1 — First spec (docs 13, 18):
L1 what SDD is and why chat-coding loses decisions → L2 write an idea (idea/IDEA_GENERAL.md) → L3 first spec with Given/When/Then → L4 approval + why the gate exists → L5 the logbook (bitacora/).
Visual learners: offer the SDD Builder (guide 51) to see specs as connected cards while they learn. / Para aprendices visuales: ofrece el SDD Builder (guía 51) para ver las specs como tarjetas conectadas.
Level 2 — Discipline (docs 14, 12, 21):
L1 EARS criteria (WHEN..., THE SYSTEM SHALL...) → L2 plan consistent with spec → L3 tasks with tests first → L4 gate + consent + implement one task → L5 session close contract and handoffs.
Level 3 — Governance (docs 15, 08, 42):
L1 sidecar vs standalone layouts → L2 Spec Kit flow (/speckit.*) on top of this template → L3 multi-agent rules (AGENTS.md, policy markers) → L4 quality gates in CI → L5 state of the art and trade-offs (doc 50: spec-anchored vs spec-as-source, waterfall critique).
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.
- 2d ago First seen · 42 lines · 44 tokens per session scan A 8499dd8d9308
tutor is a command published in the GitHub repository juanklagos/spec-driven-development-template (15 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 862 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
memorize.skeleton
Her sey kaydetmeye deger degildir. Hafiza, gelecekte TEKRAR KARSILASILDACAK bilgileri saklar. "Bunu bilseydim daha hizli yapardim" testini gec: ileride ayni durumla karsilasan ajan bu bilgiden faydalanir mi?
sugar-remember
Store a learning, decision, or preference in Sugar's memory.
f5-mode
Switch between development modes.
arch-learn
Append a learning to .claude/arch-learnings.md. Pass the learning content as the argument; the coach writes it with source=usertriggered and the appropriate appliesto scope.
sw-learn
Post-ship capture of patterns and learnings.
sdlc-retrospective
Retrospective and postmortem facilitation - blameless, action-oriented learning.