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/habib0x0/spec-driven-plugin/specgit clone --depth 1 https://github.com/Habib0x0/spec-driven-pluginWhat 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 | $0.00012 | $0.03409 |
| Opus 5 | $0.00006 | $0.01705 |
| Sonnet 5 | $0.00002 | $0.00682 |
| Haiku 4.5 | $0.00001 | $0.00341 |
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 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec Command
Create a new specification for a feature using the 3-phase spec-driven workflow. Requirements are gathered interactively with the user, then agents handle the heavy writing.
Model Routing
| Phase | Who | Model Tier | Why |
|---|---|---|---|
| Phase 0 Scan | spec-scanner agent | standard | Fast multi-file reading; reasoning depth not critical |
| Requirements Gathering | /spec command (inline) | Current model | Interactive — needs AskUserQuestion |
| Requirements + Design Writing | spec-planner agent | reasoning | Deep reasoning for edge cases and architecture |
| Tasks | spec-tasker agent | standard | Fast, structured task generation |
| Validation | spec-validator agent | standard | Checklist-based verification |
Model Override
Each agent spawn below reads a SPEC_MODEL_* environment variable. When the variable is set and non-empty, pass its value as the model: parameter to the Task tool, overriding the agent's frontmatter tier alias. When unset, omit model: from the Task invocation and the agent runs on its frontmatter default.
| Env var | Agent | Default tier |
|---|---|---|
SPEC_MODEL_SCANNER |
spec-scanner | standard |
SPEC_MODEL_PLANNER |
spec-planner | reasoning |
SPEC_MODEL_TASKER |
spec-tasker | standard |
SPEC_MODEL_VALIDATOR |
spec-validator | standard |
Example spawn with override: Task(subagent_type="spec-planner", model="$SPEC_MODEL_PLANNER", prompt=...) when SPEC_MODEL_PLANNER is set. See docs/advanced/model-routing.md for full details.
Arguments
feature-name(required): Name for the feature spec (kebab-case recommended)
Workflow
1. Initialize Spec Directory
Create the spec directory structure:
.claude/specs/<feature-name>/
├── requirements.md
├── design.md
└── tasks.md
Use templates from ${CLAUDE_PLUGIN_ROOT}/templates/ as starting points. Copy each template to the spec directory.
1.5. Phase 0: Project Profile Check
Before gathering requirements, check for (or create) a project profile so that downstream agents have codebase context.
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 · 280 lines · 12 tokens per session scan A cabfff2ceb74
spec is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 3,409 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 2026-08-31.
Other commands, from other repositories
ship
Deliver the increment. Then go live with a rollback you have run.
sruja-bugfix-triage
Systematic workflow for triaging and fixing bugs with architecture grounding.
sruja-verify-task
Run verification steps for a task profile. Use before marking a task as done.
AI: Decide
Build-vs-adopt gate — for each critical concern, decide Rent/Adopt/Extend/Fork/Build and record it as an ADR.
re-review
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
xray
Zero-config X-ray of this repo's real architecture — map, living docs, and evolution feed. No rules required.