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 shennawardana23/skillme --skill spec-driven-developmentgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/spec-driven-development)<a href="https://agentmods.dev/skills/shennawardana23/skillme/spec-driven-development"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/spec-driven-development.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 | $0.00072 | $0.01646 |
| Opus 5 | $0.00036 | $0.00823 |
| Sonnet 5 | $0.00014 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
spec-driven-development 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 4d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development
Write the spec before the code. The spec is the shared source of truth between agent and human — what's being built, why, and how "done" will be recognized — and every downstream implementation decision derives from it, not from re-interpreting the original request each time. Code without a spec is guessing dressed up as progress.
When to use
Starting a new project or feature; requirements are ambiguous or incomplete; the change touches multiple files or modules; about to make an architectural decision; the task would take more than ~30 minutes to implement.
Skip it for: single-line fixes, typo corrections, or a change where requirements are unambiguous and fully self-contained.
The gated workflow
Four phases. Don't advance until the current one is validated by a human.
SPECIFY ──→ PLAN ──→ TASKS ──→ IMPLEMENT
│ │ │ │
▼ ▼ ▼ ▼
human human human human
reviews reviews reviews reviews
1. Specify
Ask clarifying questions until requirements are concrete, and surface assumptions before writing anything else:
ASSUMPTIONS:
1. Web application, not native mobile
2. Session-based auth (not JWT)
3. PostgreSQL (matches the existing schema)
→ Correct these now, or I'll proceed with them.
Don't silently fill in ambiguous requirements — the spec's whole purpose is surfacing misunderstanding before code exists, and a silent assumption is the most dangerous kind of misunderstanding because nobody gets a chance to catch it.
Cover six areas:
- Objective — what's being built, for whom, what success looks like.
- Commands — full executable commands, not just tool names
(
npm run build, not "build it"). - Project structure — where source, tests, and docs live.
- Code style — one real snippet in the target style beats three paragraphs describing it.
- Testing strategy — framework, test locations, which levels cover which concerns.
- Boundaries — three tiers: Always (run tests before commit, validate inputs), Ask first (schema changes, new dependencies, CI config), Never (commit secrets, edit vendor directories, delete failing tests without approval).
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.
- 4d ago First seen · 179 lines · 72 tokens per session scan A 6ec7f34efb02
spec-driven-development is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,646 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
autonomous-workflow
The phase-based machinery (0–7) behind the aw dispatcher — task intake through tested PR delivery in an isolated Git worktree, with optional companion skills for planning, quality gates, TDD, UX, code quality, docs, and CI verification. Companions skip silently if not installed. NOT the entry point and not…
batch-linear-tickets
Batch-analyze and resolve multiple Linear tickets — bug fixes and feature work. For each ticket: classifies as bug or feature (auto from Linear labels, or via the --type flag), dispatches the appropriate per-ticket analysis (linear-ticket-investigator + rca-investigator for bugs, just linear-ticket-investigator for…
aw
Ships autonomous, end-to-end coding work — implement a feature or fix, all the way to a tested draft PR — from a single opt-in entry point. Detects the task tier (Micro / Lite / Full) and routes: Micro/Lite run single-pass in this context; Full hands off to the aw-planner → aw-executor agents. Use when the user asks…
openspec-implementation
A workflow for implementing an approved technical specification one task at a time. It reads the proposal, makes the changes, runs tests, and validates the result.
codely-plan-create-github
Create a plan for the specified task and store it as GitHub issues in the repository of the current working directory. Given the URL of a GitHub issue, it turns that issue into the parent "plan" issue (Goal, Context and a checklist of phases) and creates one child issue per phase, linking every phase as a native…
codely-plan_phase-implement-github
Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL of a phase (child) issue it implements that phase; given the parent plan issue it finds and implements the current phase. Only implements a single phase per invocation, then stops for user review. It…