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-docsgit 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 | $0.00610 |
| Opus 5 | $0.00006 | $0.00305 |
| Sonnet 5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
spec-docs 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-docs Command
Generate documentation from spec files and implemented code. Produces API references, user guides, architecture decision records, and operations runbooks as appropriate.
Philosophy
Specs are internal dev artifacts. Users, API consumers, and ops teams need different documentation. This command bridges that gap by generating targeted docs from the spec + actual implementation code.
Workflow
1. Locate the Spec
If a spec name is provided, use it. Otherwise auto-detect from .claude/specs/.
2. Analyze What's Needed
Read the spec files and implementation to determine the feature type:
| Feature Type | Detected By | Docs Generated |
|---|---|---|
| API/Backend | API endpoints in design.md, server routes in code | API Reference, ADR |
| UI/Frontend | Components in design.md, UI files in code | User Guide, Component Ref |
| Full-Stack | Both API + UI elements | All docs |
| Library/SDK | Exported functions, package.json lib config | API Reference, Getting Started |
| Infrastructure | Deployment configs, CI/CD, env vars | Runbook, ADR |
Present the detected type and planned documents to the user via AskUserQuestion:
- Generate all recommended docs — Proceed with the detected set
- Let me choose which docs — Pick from the list
- Custom output location — Specify where docs should be written
Default output location: .claude/specs/<feature-name>/docs/
3. Spawn the Documenter Agent
Delegate to the spec-driven:spec-documenter agent via the Task tool.
Pass the agent:
- The spec directory path
- Which documents to generate
- The output directory
- Any user preferences about documentation style or audience
4. Present Results
When the documenter returns:
- List all generated documents with brief descriptions
- Highlight any discrepancies found between design.md and actual implementation
- Note any documentation that couldn't be generated (and why)
Ask the user via AskUserQuestion:
- Looks good — Done
- Move docs to project root — Copy from spec dir to project
docs/folder - Regenerate specific docs — Re-run with adjustments
- Edit manually — User will refine the generated docs themselves
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 · 76 lines · 12 tokens per session scan A 308efa4f8fde
spec-docs 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 610 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.