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 incremental-implementationgit 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/incremental-implementation)<a href="https://agentmods.dev/skills/shennawardana23/skillme/incremental-implementation"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/incremental-implementation/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/shennawardana23/skillme/incremental-implementation"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/incremental-implementation.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 | $0.00070 | $0.01631 |
| Opus 5 | $0.00035 | $0.00816 |
| Sonnet 5 | $0.00014 | $0.00326 |
| Haiku 4.5 | $0.00007 | $0.00163 |
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 6d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incremental Implementation
Build in thin vertical slices: implement one piece, test it, verify it, commit, then expand. Each increment leaves the system in a working, testable state. This is the execution discipline that turns "implement the whole feature" from one large, unverifiable leap into a sequence of small, individually-checked steps.
When to use
Any multi-file change; building a feature from a task breakdown; refactoring existing code; any time about to write more than ~100 lines before running anything.
Skip it for: a single-file, single-function change where the scope is already minimal.
The increment cycle
Implement ──→ Test ──→ Verify ──→ Commit ──→ next slice
- Implement the smallest complete piece of functionality.
- Test — run the suite, or write a test if none covers this yet.
- Verify the slice works (tests pass, build succeeds, or a manual check for something not yet automatable).
- Commit with a descriptive message covering this slice only.
- Move to the next slice — carry forward, don't restart from scratch.
Slicing strategies
Vertical (preferred) — one complete path through the whole stack per slice:
Slice 1: create a task (DB + API + minimal UI) → user can create via the UI
Slice 2: list tasks (query + API + UI) → user can see their tasks
Slice 3: edit a task (update + API + UI) → user can modify tasks
Slice 4: delete a task (+ confirmation) → full CRUD complete
Each slice delivers working, end-to-end functionality — never "all of the database layer, then all of the API, then all of the UI," which leaves nothing demonstrably working until the very last slice lands.
Contract-first — when backend and frontend need to proceed in parallel: define the API contract (types/interfaces/OpenAPI) first, then implement backend against it and frontend against mock data matching it, then integrate.
Risk-first — tackle the riskiest or most uncertain piece first (e.g. prove a WebSocket connection works) so a fundamental blocker surfaces before slices 2 and 3 are built on top of an unproven foundation.
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.
- 6d ago First seen · 168 lines · 70 tokens per session scan A b6da5dfd0d75
incremental-implementation is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,631 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 2026-09-03.
Other skills, from other repositories
implement-suggestion
Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS contains PR URLs; empty $ARGUMENTS auto-detects the active PR) per PR: resolves a worktree, fetches every actionable comment from both human teammates AND AI code-review bots (claude[bot], coderabbitai[bot], …)…
pr-review
One-shot read-only review of a GitHub PR — dispatches the pr-reviewer agent and reports its verdict and findings without touching your code. The short entry point for "review this PR" when you do not want an apply-and-converge loop. Also writes maintainer relevance rules via /pr-review remember . Invoke with…
codely-git-conventional_commit
Create a git commit following the team's Conventional Commit conventions. Use when the user asks to commit changes or create a commit.
create-commit
Compose and create a git commit whose message follows the Angular Conventional Commits standard, so semantic-release can version and changelog it automatically. Use this skill whenever the user wants to commit staged changes, "make a commit", "commit this", "write a commit message", "commit with conventional/angular…
create-draft-pr
Commit, push, and create a draft PR using the pr-description format, with UX flow context when relevant.
wrap-phase
Wraps up a development phase by cleaning AGENTSYNC.md, summarizing work, and committing changes.