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 skills/changoo89/claude-pilot/spec-driven-workflownpx skills add changoo89/claude-pilot --skill spec-driven-workflowgit clone --depth 1 https://github.com/changoo89/claude-pilotWrote 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/changoo89/claude-pilot/spec-driven-workflow)<a href="https://agentmods.dev/skills/changoo89/claude-pilot/spec-driven-workflow"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/spec-driven-workflow.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01930 |
| Opus 5 | $0.00014 | $0.00965 |
| Sonnet 5 | $0.00005 | $0.00386 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
spec-driven-workflow 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 5d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Spec-Driven Workflow (Planning)
Purpose: Analyze codebase and create SPEC-First execution plan through dialogue (read-only phase) Target: Planner Agent executing /00_plan command
Quick Start
When to Use This Skill
- Create new implementation plan
- Explore codebase for task requirements
- Gather user requirements through dialogue
Quick Reference
# Invoked by: /00_plan "task description"
# Output: Complete plan in .pilot/plan/draft/ + user decision
Core Philosophy
Read-Only: NO code modifications, only exploration/analysis/planning | SPEC-First: Requirements before implementation | Efficient Dialogue: Ask user only for business/intent; handle technical details autonomously or via GPT
What This Skill Covers
In Scope: Codebase exploration (parallel agents), requirement gathering, SPEC-First plan (PRP framework), decision tracking, dialogue with question filtering Out of Scope: Implementation → execute-plan/SKILL.md | Confirmation → confirm-plan/SKILL.md
EXECUTION DIRECTIVE
DIALOGUE PHASE - NOT EXECUTION: ASK only when necessary (filter first) | WAIT for response | NEVER auto-execute /01_confirm or /02_execute | Selection ≠ Execution (user chooses approach → continue planning, NOT implement)
Question Filtering (CRITICAL)
Self-Decide (do NOT ask): Technical details (file naming, folder structure), obvious patterns, standard practices, minor trade-offs Consult GPT First: Architecture decisions, security, complex trade-offs (use gpt-delegation skill → "read-only" mode) MUST Consult GPT: Architecture keywords OR confidence < 0.5 → MUST consult before AskUserQuestion (REFERENCE.md, gpt-delegation/SKILL.md) Ask User ONLY: Business requirements, direction choices (2+ genuinely different outcomes), scope clarification, user intent ambiguity
Execution Steps
Step 0: Initialize Progress Tracking
Create TaskCreate entry for planning phase (TaskCreate analyzing - marks /00_plan start).
What ships with it
1 file 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.
- 5d ago First seen · 166 lines · 27 tokens per session scan A 3be87c020b26
spec-driven-workflow is a skill published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 1,930 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 skills, from other repositories
loop-forge
Turn a one-line description of a repetitive task into a reusable, self-guarding slash command. loop-forge diagnoses the task into one of 5 loop shapes (Batch / Pipeline / Refine / Watch / Explore), interviews for the blanks, and auto-injects two safety devices the user didn't know they needed — an independent verifier…
skill-factory
Analyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로", "스킬 만들어", "이거 스킬로", "skill factory", "이 작업 자동화해", "스킬 추출", "make this a skill", "extract skill", "convert to skill", "스킬 팩토리", "자동 스킬 생성". Differs from skill-creator (archived) and manage-skills (drift…
harness-diet
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to reference files, convert rules to path-scoped or skill-triggered loading, and verify zero governance loss with deterministic preservation checks. Use on "harness…
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.