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 incremental-implementationgit 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/incremental-implementation)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/incremental-implementation"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/incremental-implementation.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 | $0.00067 | $0.01430 |
| Opus 5 | $0.00034 | $0.00715 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
incremental-implementation 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 7d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incremental Implementation
Adapted from
addyosmani/agent-skillsunder the MIT License. Copyright (c) Addy Osmani. Per-slice two-stage review pattern + continuous-execution rule adapted fromobra/superpowers/skills/subagent-driven-developmentunder MIT.
The principle: every PR is mergeable on its own. No "wait for the next one" merges. No multi-week branches. Vertical = touches every layer (UI / API / DB / tests) for one narrow capability rather than completing one layer fully before moving to the next.
When to invoke
- A spec or plan is ready and the user is about to start coding
- The user says "this should be a multi-PR change"
- A change exceeds 500 LOC or touches >5 files
Process
Step 1: Confirm a slice plan exists
If planning-and-task-breakdown produced a list of tasks, use that. Otherwise produce a slice plan now: 3-7 vertical slices, each ≤500 LOC, each with its own acceptance criteria.
Step 2: Pick the first slice
Hardest invariant first if possible (proves the design); easiest first if morale is needed (early win).
Step 3: Implement behind a feature flag
if (featureFlags.kaijutsuV2) { /* new path */ } else { /* old path */ }
The flag defaults OFF in main. Old behavior is preserved. New behavior ships when the flag flips.
Step 4: Tests + green CI
Every slice ends with: passing unit tests for the new code, no regression in existing tests, lint clean, type-check clean. If CI is red, the slice isn't done.
Step 5: Per-slice two-stage review chain
A slice is NOT complete after the implementer says "done". Run two reviews in order; only after BOTH pass does the slice get marked shippable.
Stage A — Spec compliance review. Dispatch a fresh subagent (clean context, no implementation history) with:
- The slice's declared acceptance criteria from the plan
- The slice's diff (
git diff <base>..<head>) - One question: "Does this diff satisfy every acceptance criterion? Pass / fail per criterion + reasons."
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.
- 7d ago First seen · 103 lines · 67 tokens per session scan A 76f8e5af052d
incremental-implementation is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,430 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
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…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".