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/spec-validategit 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 | $0.00009 | $0.00888 |
| Opus 5 | $0.00005 | $0.00444 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
spec-validate 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-validate Command
Validate that a spec is complete, consistent, and ready for implementation.
Workflow
1. Identify Spec
Look for existing specs in .claude/specs/:
If multiple specs exist, ask which one to validate.
2. Check File Completeness
Verify all spec files exist:
- requirements.md exists
- design.md exists
- tasks.md exists
3. Validate Requirements
Check requirements.md for:
Structure
- Has overview section
- Has user stories section
- Each story has As a/I want/So that format
- Each story has acceptance criteria
EARS Notation
- All criteria use WHEN/THE SYSTEM SHALL format
- Criteria are specific and testable
- No vague terms ("quickly", "easily", "properly")
Completeness
- Non-functional requirements defined
- Out of scope section exists
- Open questions resolved (none marked with [ ])
4. Validate Design
Check design.md for:
Structure
- Has architecture overview
- Has component specifications
- Has data models defined
Coverage
- All requirements addressable by design
- Each component has clear purpose
- Interfaces defined between components
Quality
- Security considerations documented
- Performance considerations documented
- Alternatives considered with rationale
5. Validate Tasks
Check tasks.md for:
Structure
- Tasks organized by phase
- Each task has required fields (status, requirements, description, acceptance, dependencies)
Traceability
- All requirements have corresponding tasks
- No orphan tasks (tasks without requirement links)
- Dependencies form valid DAG (no cycles)
Quality
- Task descriptions are specific
- Acceptance criteria are testable
- Dependencies are reasonable
6. Cross-Reference Validation
Check consistency across files:
- Requirements IDs in tasks.md match requirements.md
- Components in tasks.md match design.md
- No contradictions between documents
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 · 168 lines · 9 tokens per session scan A 8c863575b4d3
spec-validate is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 888 once invoked, about $0.0000 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
receipts
Find the receipt. A dated line, or it did not happen.
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.
triage
AI-powered reachability triage for dependency vulnerabilities. Scans for CVEs then searches your source code to estimate whether each vulnerable API is actually called. Outputs a prioritized FOUNDINSOURCE / UNCERTAIN / NOTFOUNDINGREP report.
smart-help
Context-aware help that suggests relevant commands.
crossframe-essay
使用 CrossFrame Essay 把用户给出的主题、素材或问题写成中文批判性洞察文章。.