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 skills add marcusgoll/Spec-Flow --skill specification-phasegit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/marcusgoll/spec-flow/specification-phase)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/specification-phase"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/specification-phase/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/specification-phase"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/specification-phase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00086 | $0.06166 |
| Opus 5.5 | $0.00034 | $0.02466 |
| Sonnet 5.5 | $0.00017 | $0.01233 |
| Haiku 4.5 | $0.00009 | $0.00617 |
Grade A, and why
specification-phase 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 1mo 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 — 739 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill orchestrates the /specify phase, producing spec.md with measurable success criteria, classification flags for downstream workflows, and maximum 3 clarifications using informed guess heuristics for technical defaults.
Core responsibilities:
- Parse and normalize feature input to slug format (kebab-case, no filler words)
- Check roadmap integration to reuse existing context
- Load project documentation context (docs/project/) to prevent hallucination
- Classify feature with 4 flags (HAS_UI, IS_IMPROVEMENT, HAS_METRICS, HAS_DEPLOYMENT_IMPACT)
- Determine research depth based on complexity (FLAG_COUNT: 0→minimal, 1→standard, ≥2→full)
- Apply informed guess strategy for non-critical technical decisions
- Generate ≤3 clarifications (only scope/security critical)
- Write measurable success criteria (quantifiable, user-facing)
Inputs: User's feature description, existing roadmap entries, project docs (if exists), codebase context Outputs: specs/NNN-slug/spec.md, NOTES.md, state.yaml, updated roadmap (if FROM_ROADMAP=true) Expected duration: 10-15 minutes
<quick_start> Execute /specify workflow in 9 steps:
- Parse and normalize input - Generate slug (remove filler words: "add", "create", "we want to"), assign feature number (NNN)
- Check roadmap integration - Search roadmap for slug match, reuse context if found (saves ~10 minutes)
- Load project documentation - Extract tech stack, API patterns, existing entities from docs/project/ (prevents hallucination)
- Classify feature - Set HAS_UI, IS_IMPROVEMENT, HAS_METRICS, HAS_DEPLOYMENT_IMPACT flags using decision tree
- Determine research depth - FLAG_COUNT → minimal (0), standard (1), full (≥2)
- Apply informed guess strategy - Use defaults for performance (<500ms), rate limits (100/min), auth (OAuth2), retention (90d logs)
- Generate clarifications - Max 3 critical clarifications (scope > security > UX > technical priority matrix)
- Write success criteria - Measurable, quantifiable, user-facing outcomes (not tech-specific)
- Generate artifacts and commit - Create spec.md, NOTES.md, state.yaml, update roadmap
Key principle: Use informed guesses for non-critical decisions, document assumptions, limit clarifications to ≤3. </quick_start>
<knowledge_requirements> Required understanding before execution:
- Classification decision tree: UI keywords vs backend-only exclusions, improvement = baseline + target, metrics = user tracking, deployment = env vars/migrations/breaking changes
- Informed guess heuristics: Performance (<500ms), retention (90d logs, 365d analytics), rate limits (100/min), auth (OAuth2), error handling (user-friendly + error ID)
- Clarification prioritization matrix: Critical (scope, security, breaking changes) > High (UX) > Medium (performance SLA, tech stack) > Low (error messages, rate limits)
- Slug generation rules: Remove filler words, lowercase kebab-case, 50 char limit, fuzzy match roadmap
See reference.md for complete decision trees and heuristics. </knowledge_requirements>
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 739 lines · 86 tokens per session scan A 60d8cae2a8e7
specification-phase is a skill published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 23d ago), licensed MIT. It adds 86 tokens to every session and 6,166 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
aria
Designs the data model, API contracts, and structural foundation of the system.
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.