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 mostafa-drz/claude-skills --skill build-incrementalgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/build-incremental)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/build-incremental"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/build-incremental/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/mostafa-drz/claude-skills/build-incremental"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/build-incremental.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 | $0.00060 | $0.01640 |
| Opus 5.5 | $0.00024 | $0.00656 |
| Sonnet 5.5 | $0.00012 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
build-incremental 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build
Implement code in progressive, verified increments. Each unit is built, checked, and committed before moving to the next.
Preferences
Read ~/.claude/skills/build-incremental/preferences.md using the Read tool. If not found, no preferences are set.
Project context
On startup, use Bash to detect: project stack files (ls package.json Cargo.toml pyproject.toml go.mod Makefile), CLAUDE.md presence, current git branch, and git status. Skip any that fail.
Command routing
Check $ARGUMENTS:
help→ display help then stopconfig→ interactive setup then stopreset→ delete~/.claude/skills/build-incremental/preferences.md, confirm, stop--dry-run <description>→ show the plan without executing then stop--no-commit <description>→ build and verify but don't commit--skip-lint <description>→ skip linting, only run type checks- anything else → proceed with build
Help
Build — Implement code in verified increments
Usage:
/build-incremental <what to build> Build incrementally with checks + commits
/build-incremental --dry-run <description> Show plan without executing
/build-incremental --no-commit <description> Build and verify, don't commit
/build-incremental --skip-lint <description> Skip lint, only typecheck
/build-incremental config Set toolchain and commit preferences
/build-incremental reset Clear preferences
/build-incremental help This help
Examples:
/build-incremental add user settings page with form validation
/build-incremental Milestone 2 from IMPLEMENTATION_PLAN.md
/build-incremental --dry-run refactor auth middleware
How it works:
1. Detects your toolchain (or reads from preferences)
2. Breaks work into committable units
3. For each unit: implement → check → fix → commit
4. Reports summary with all commits
Current preferences:
(shown above under Preferences)
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 Changed · +3 lines f902609a75a0
- 1mo ago First seen · 186 lines · 60 tokens per session scan A 6fac417987ae
build-incremental is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,640 once invoked, about $0.0002 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
ship
Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
056-design-avoid-breaking-changes
Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…
quick-finalize
Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the…
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
verification-loop
After a feature or refactor on this Windows estate, run six checks in order and write a PASS or FAIL note before a draft pull request. Use when work is about to be committed, pushed, or handed to another harness.
test-suite-prioritizer
Analyzes test suites and suggests optimal test execution order based on code change impact and project requirements. Use when optimizing CI/CD pipelines, deciding which tests to run before committing, or selecting critical tests under time constraints. Prioritizes tests by analyzing recently modified files, test…