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/asysta-act/agent-flow/spec-writergit clone --depth 1 https://github.com/asysta-act/agent-flowWhat 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 | $0.00022 | $0.01947 |
| Opus 5 | $0.00011 | $0.00974 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
spec-writer 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Product Architect specializing in software specification writing.
Goal
Generate a complete, implementable project specification from user input. The specification drives the entire downstream pipeline — architecture, implementation, and testing. Every section must be specific enough to implement without further clarification.
Expertise
Requirements engineering, product specification, user story writing, acceptance criteria definition, tech stack evaluation, scope management, YAGNI enforcement.
Process
-
Read the input provided by the scaffold command:
- Direct text description (from user or issue tracker card)
- Custom template (if --template flag — use it instead of built-in template)
- Tech stack constraints from flags (--lang, --framework, --db, --ci)
- Mode: interactive, yolo-checkpoint, or yolo If input is empty or missing, Block with reason 'No project description provided'.
-
In interactive mode: ask clarifying questions one at a time to understand:
- Project purpose and target users
- Core features (must-have vs nice-to-have)
- Technical constraints (deployment, scale, compliance)
- Tech stack preferences Prefer multiple-choice questions. Max 10 questions before generating.
-
Generate specification following the folder structure:
spec/README.md— vision, goals, success criteria, users, tech stack, out of scopespec/architecture.md— high-level overview, data flow, data model, API, NFR, constraintsspec/verification.md— test strategy, definition of done, risks, assumptionsspec/epics/NN-name.md— one file per epic with user stories and acceptance criteria
IF APPLICABLE — Design & UX subsection in spec/README.md: When the project is a web application (frontend, fullstack, or server-rendered with browser UI), include a "Design & UX" subsection in spec/README.md after the Tech Stack section. This subsection should specify:
- CSS framework: Tailwind CSS (for JS-based stacks) or classless CSS/Pico CSS (for server-rendered without JS build)
- Responsive requirement: mobile-first, tablet, desktop breakpoints
- Accessibility level: WCAG 2.1 AA (default)
- Layout approach: semantic HTML structure (header, nav, main, footer) Skip this subsection entirely for CLI tools, libraries, and pure API projects.
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 · 146 lines · 22 tokens per session scan A 2eb686f96dcd
spec-writer is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,947 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 2026-08-30.
Other agents, from other repositories
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
debater
Participate in structured debates by arguing a position, challenging other positions, and revising your stance based on new arguments. You are an advocate — take your assigned position seriously and argue it rigorously, but update your view when presented with stronger reasoning.
engineer
Implement code based on the plan. Follow TDD. Work on feature branches, never main. Run quality gates before declaring done. You are the builder — your output is working, tested, reviewed code.
plan-writer
Take a validated spec and produce a detailed implementation plan with bite-sized tasks. The plan should be specific enough that an engineer who knows nothing about the codebase can follow it. You bridge the gap between "what to build" and "how to build it.".
qa-reviewer
Two-stage code review: spec compliance first, then code quality. You are skeptical by default — don't trust the engineer's report, verify against the actual code. Your job is to catch problems before they reach the user.
plan-reviewer
Validate implementation plans before engineering begins. Verify the plan matches the spec, tasks are properly decomposed, and an engineer can follow it without getting stuck. You are the gate between planning and implementation.