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 agentmods add skills/developersglobal/ai-agent-skills/incremental-codingnpx skills add DevelopersGlobal/ai-agent-skills --skill incremental-codinggit clone --depth 1 https://github.com/DevelopersGlobal/ai-agent-skillsWhat 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 | $0.00030 | $0.00537 |
| Opus 5 | $0.00015 | $0.00269 |
| Sonnet 5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
incremental-coding 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The biggest risk in software development is building a lot of code that doesn't work. Incremental coding limits this risk: build a little, verify it works, build more. At every step, the system is in a known-good state.
When to Use
- Any implementation that will take more than 2 hours
- When building in a complex domain you're uncertain about
- When multiple components need to integrate
Process
Step 1: Define the First Increment
- What is the smallest possible thing you can build that provides value and can be verified?
- It doesn't have to be feature-complete — just correct and verifiable.
- Example: "Add the endpoint skeleton with hardcoded response" before adding business logic.
Verify: The first increment can be verified in under 5 minutes.
Step 2: Build → Verify → Commit
- Build only the first increment.
- Run tests. Verify manually if needed. Confirm it works.
- Commit this working state.
- Repeat for the next increment.
Verify: There is a working commit after each increment.
Step 3: Integration Continuously
- Integrate with the real system as early as possible — not at the end.
- Test against real dependencies (DB, API, etc.) as early as possible.
- Fake integrations (mocks) should be replaced with real ones by the end.
Verify: By completion, all mocks replaced with real integration.
Common Rationalizations (and Rebuttals)
| Excuse | Rebuttal |
|---|---|
| "I need to build it all to know if it works" | No. Build the first piece and test it. Uncertainty is always reducible. |
| "Integration is at the end" | Integration pain is proportional to time since last integration. Integrate continuously. |
Verification
- Implementation built in verifiable increments
- Working commit exists after each increment
- No long stretches of "broken" state in git history
- All mocks replaced with real integrations by completion
References
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.
- 2d ago First seen · 64 lines · 30 tokens per session scan A 0a252b683d93
incremental-coding is a skill published in the GitHub repository DevelopersGlobal/ai-agent-skills (65 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 537 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…