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 momentmaker/kaijutsu --skill spec-driven-developmentgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/spec-driven-development)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/spec-driven-development"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/spec-driven-development/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/momentmaker/kaijutsu/spec-driven-development"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/spec-driven-development.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 | $0.00088 | $0.01663 |
| Opus 5.5 | $0.00035 | $0.00665 |
| Sonnet 5.5 | $0.00018 | $0.00333 |
| Haiku 4.5 | $0.00009 | $0.00166 |
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 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development
Adapted from
addyosmani/agent-skillsunder the MIT License. Copyright (c) Addy Osmani. Modifications by kaijutsu maintainers — wrapped in the kaijutsu schema, with the final review pass migrated tojutsu swarm doc-review(the universal QA gate).
A spec is a workflow artifact, not an essay. The deliverable is a markdown file that the user (and future agent sessions) can read in 5 minutes and act on.
When to invoke
- User describes a problem fuzzy ("we should make it faster", "users keep getting confused")
- User asks for "a plan" before any implementation begins
- A change spans more than one file or one obvious step
- The agent is about to start coding without first writing what they're going to build
Process
Step 1: Capture the problem
Ask the user — or write down — what problem this solves. Not the solution, the problem. Format:
Problem: <one sentence>
Who feels it: <user persona, role, or system>
When: <conditions / triggers / frequency>
Today's workaround: <what people do now>
Cost of doing nothing: <what breaks / stays broken>
If you can't fill this in cleanly, the spec is premature — go back to the user with clarifying questions.
Step 2: Scope + non-goals
Two equally important sections:
In scope: <bullet list — what this change WILL deliver>
Non-goals: <bullet list — what this change explicitly does NOT cover>
Non-goals are the discipline. Without them every spec becomes "fix everything." Aim for at least 3 explicit non-goals.
Step 3: Acceptance criteria
Concrete, observable, falsifiable:
- [ ] <user-facing behavior or system property>
- [ ] <test that passes>
- [ ] <metric that moves>
If a criterion can't be checked by reading the diff, running a command, or observing behavior, it's prose — drop it.
Step 4: Open questions + risks
Open questions:
- Q1: <decision the user / team needs to make>
- Q2: ...
Risks:
- <thing that could derail this; mitigation if known>
What ships with it
2 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 · 147 lines · 88 tokens per session scan A 05485aa596f1
spec-driven-development is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 1,663 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.