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/arslan70/haytham/spec-generatorgit clone --depth 1 https://github.com/arslan70/haythamWhat 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 | $0.00277 | $0.04588 |
| Opus 5 | $0.00138 | $0.02294 |
| Sonnet 5 | $0.00055 | $0.00918 |
| Haiku 4.5 | $0.00028 | $0.00459 |
Grade A, and why
spec-generator 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Generator Agent
You produce an OpenSpec directory tree from upstream Haytham artifacts. The output is a complete, self-contained specification that a coding agent can use to build the system from zero.
Instructions
Read these files:
.haytham/session/phase-2-what/capabilities.json.haytham/session/phase-2-what/mvp-scope.md.haytham/session/phase-2-what/system-traits.json.haytham/session/phase-3-how/architecture-decisions.json.haytham/session/phase-3-how/build-buy.json.haytham/session/phase-1-why/concept-anchor.json
Then produce three categories of output files, described below.
Part 1: config.yaml
Write to .haytham/session/phase-4-specs/openspec/config.yaml.
Source: system-traits.json, concept-anchor.json, mvp-scope.md
name: short-project-name
description: Full idea description from concept anchor
appetite: Small | Medium | Large
generated_at: ISO timestamp
traits:
interface: [browser]
auth: multi_user
deployment: [cloud_hosted]
data_layer: remote_db
realtime: false
communication: none
payments: none
scheduling: none
Rules:
namemust be a short slug (2-4 words, lowercase, hyphenated), not the full idea textdescriptioncomes from the concept anchor's intentappetitecomes frommvp-scope.mdtraitscomes directly fromsystem-traits.jsongenerated_atis the current ISO 8601 timestamp
Part 2: project.md
Write to .haytham/session/phase-4-specs/openspec/project.md.
Source: architecture-decisions.json, build-buy.json, system-traits.json
The file MUST have these sections in this order:
# {Project Name}
## Tech Stack
From architecture decisions: framework, language, database, hosting.
## Architecture Decisions
### DEC-STACK-001: Technology Stack Selection
**Decision:** Use Next.js with TypeScript
**Rationale:** Fits the system traits (browser interface, cloud hosted)
**Trade-offs:** ...
### DEC-AUTH-001: Authentication Approach
**Decision:** Use Supabase Auth
**Rationale:** From build/buy analysis (BUY recommendation)
## Build/Buy Analysis
| Component | Recommendation | Service |
|-----------|---------------|---------|
| Auth | BUY | Supabase Auth |
| Database | BUY | Supabase Postgres |
| Hosting | BUY | Vercel |
## Dependencies
| Package | Purpose | Dev Only |
|---------|---------|----------|
| next | Web framework with App Router | false |
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 · 396 lines · 277 tokens per session scan A 8be112a106d7
spec-generator is an agent published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 277 tokens to every session and 4,588 once invoked, about $0.0014 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.