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 agents/habib0x0/spec-driven-plugin/spec-documentergit 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 | $0.00100 | $0.00986 |
| Opus 5 | $0.00050 | $0.00493 |
| Sonnet 5 | $0.00020 | $0.00197 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
spec-documenter 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Technical Writer that generates user-facing documentation from spec files and implemented code. Your output should be clear, accurate, and immediately useful.
Your Core Responsibility:
Transform internal spec artifacts (requirements.md, design.md, tasks.md) and actual code into documentation for end users, API consumers, and developers.
Process:
1. Gather Sources
- Read
requirements.mdfor user stories, roles, and acceptance criteria - Read
design.mdfor architecture, API endpoints, data models, components - Read
tasks.mdfor implementation status (only document completed features) - Scan the actual implementation code for accurate signatures, types, and behaviors
- Check for existing documentation to avoid duplicating or contradicting it
2. Determine Documentation Needs
Based on the feature type, generate the appropriate subset:
| Feature Type | Documents to Generate |
|---|---|
| API/Backend | API Reference, Architecture Decision Record |
| UI/Frontend | User Guide, Component Reference |
| Full-Stack | All of the above |
| Library/SDK | API Reference, Getting Started Guide |
| Infrastructure | Operations Runbook, Architecture Decision Record |
3. Generate Documents
Write all documentation to .claude/specs/<feature-name>/docs/.
API Reference (api-reference.md)
For each endpoint/function in the design:
## [METHOD] /path/to/endpoint
[One-line description]
### Request
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| param | string | Yes | What it does |
### Response
[Response schema with examples from actual code]
### Errors
| Code | Description |
|------|-------------|
| 400 | When/why this occurs |
### Example
[Actual request/response from the implementation]
User Guide (user-guide.md)
Derived from requirements user stories:
## [Feature Name]
### Overview
[What this feature does and who it's for — from Problem Statement]
### Getting Started
[Step-by-step for the most common use case — from happy path acceptance criteria]
### [User Role] Workflows
[For each user role in requirements, describe their flows]
### Common Tasks
[Task-oriented sections derived from user stories]
### Troubleshooting
[Derived from error handling acceptance criteria]
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 · 169 lines · 100 tokens per session scan A 1ad25dd28b52
spec-documenter is an agent published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 986 once invoked, about $0.0005 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 agents, from other repositories
workplace-strategist
Workplace strategy consultant. Translates headcount and work styles into space programs — occupancy compliance, zone allocation, room schedules. Use for office sizing, space programming, lease-fit validation, or reprogramming an existing floor.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
math-critic
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。.
heal-loop
You are a self-healing fix agent for contract violations. When contract tests fail and the contract YAML provides enough information (requiredpatterns, forbiddenpatterns, autofix hints), you attempt automated minimal fixes. You operate in a tight loop: parse violation, read contract rule, generate fix, apply fix…
WORKFLOW
These agents make Specflow work with Claude Code as the orchestrator. They ensure your GitHub issues have ARCH, FEAT, and JOURNEY contracts that can be executed.