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/specgit 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/spec)<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/spec"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/spec.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 | $0.00014 | $0.11146 |
| Opus 5 | $0.00007 | $0.05573 |
| Sonnet 5 | $0.00003 | $0.02229 |
| Haiku 4.5 | $0.00001 | $0.01115 |
Grade A, and why
spec 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec — Specification-Driven Development
"Plan the work, then work the plan."
Purpose
Create a comprehensive specification document before writing any code — defining WHAT to build and WHY, not HOW. This ensures alignment on requirements, constraints, and acceptance criteria.
Usage
| How to invoke | Result |
|---|---|
/spec <requirements> |
Generate SPEC.md + (if the product has a UI) ASCII wireframes. This is the default — does NOT generate an HTML prototype. |
/spec <requirements> --prototype |
As above, plus a clickable HTML prototype. Can also be triggered in plain language: add "with prototype" / "include prototype" to the request. |
/spec --wireframes (brownfield REVERSE only) |
Opt-in as-is wireframes for the REVERSE baseline (default: waived) — either during the REVERSE run, or post-hoc over an existing baseline (documentation supplement; see §Brownfield Mode → Wireframe supplement). Plain language works too: "kèm wireframe". No-op outside REVERSE — wireframes are already always-produced for UI products. --prototype is NOT accepted in REVERSE (the running app is the click-through truth). |
/spec --propose-goals (brownfield REVERSE only) |
Opt-in labeled goal proposals when the repo has no goals evidence: the BA drafts Business/Product goals + Business Need/Expected Outcomes inferred from observed product behavior, each marked 📝P-nn + provenance + an Open Questions row for the PO to confirm (see §Brownfield Mode → Goals proposal). Numbers (KPI values, baselines, timeframes) are NEVER invented — those cells stay [NEEDS PO]. Default without the flag: the orchestrator asks at run time (propose vs plain N/A); works post-hoc over an approved baseline too. |
/spec --scope <selector> (brownfield REVERSE only) |
Scoped REVERSE — reverse-engineer only the named feature group / endpoints instead of the whole repo: for a large legacy system onboarded incrementally, or when only part of a system is being taken over / ported. Selectors are comma-separated, matched (case-insensitive substring) against the CODEBASE_MAP.md endpoint-inventory columns — route, handler, or module: --scope "/api/v1/bookmarks,/api/v1/tags" · --scope BookmarksController · --scope module:Billing. No match, or a match that would select everything → STOP and print what matched: silently reversing nothing (or the whole repo) is worse than stopping. See §Brownfield Mode → Scoped REVERSE. |
/spec (no arguments) |
See Phase 0: repo already has code → brownfield (needs /discover first); nothing there → ask the user to provide requirements. |
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 · 274 lines · 14 tokens per session scan A eca70efa5902
spec is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 11,146 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
brooks-audit
Run a Brooks-Lint architecture audit.
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
verify
Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.
fix
⚡⚡ Analyze and fix small issues [AUTO DETECT COMPLEXITY].
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.