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 varunk130/ai-workflow-playbooks --skill incremental-verificationgit clone --depth 1 https://github.com/varunk130/ai-workflow-playbooksWrote 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/varunk130/ai-workflow-playbooks/incremental-verification)<a href="https://agentmods.dev/skills/varunk130/ai-workflow-playbooks/incremental-verification"><img src="https://agentmods.dev/badge/skills/varunk130/ai-workflow-playbooks/incremental-verification/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/varunk130/ai-workflow-playbooks/incremental-verification"><img src="https://agentmods.dev/badge/skills/varunk130/ai-workflow-playbooks/incremental-verification.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 | $0.00021 | $0.00874 |
| Opus 5.5 | $0.00008 | $0.00350 |
| Sonnet 5.5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
incremental-verification 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incremental Verification
What This Skill Enables
An agent that confirms correctness at every micro-step - after every function, every file change, every integration point - rather than building a large body of code and hoping it works. Without this skill, agents produce code that looks plausible but fails at runtime, and bugs compound silently until the system is too broken to debug efficiently.
Core Competencies
1. The Verify-As-You-Go Loop
After every meaningful change, run a verification:
Write code → Verify → Commit → Next change
↑ |
└────────────────────────────┘
Verification methods by change type:
| Change | Verification |
|---|---|
| New function | Run its unit test |
| Modified function | Run existing tests + new test for the change |
| New API endpoint | Send a test request, check response shape and status |
| UI component | Render it, check the DOM/accessibility tree |
| Configuration change | Restart the service, verify it loads without errors |
| Database migration | Run the migration, verify the schema matches expectations |
2. Build Verification
Before writing new code, confirm the current state is clean:
- Run the full test suite - all green? Proceed
- Run the build command - compiles without errors? Proceed
- Run the linter - no new violations? Proceed
If any of these fail before you've made changes, flag it immediately. Do not write code on top of a broken foundation.
3. Assertion Density
Write assertions liberally during development:
- After fetching data: assert it has the expected shape
- After transforming data: assert the output matches expectations
- After calling an external service: assert the response status is successful
- After state transitions: assert the new state is valid
These can be formal tests or temporary debug assertions that get removed later - the point is catching errors at the moment they occur, not ten steps later.
4. Regression Detection
After every change, verify nothing broke:
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 · 92 lines · 21 tokens per session scan A d6f958024d0a
incremental-verification is a skill published in the GitHub repository varunk130/ai-workflow-playbooks (2 stars, last pushed 24d ago), licensed MIT. It adds 21 tokens to every session and 874 once invoked, about $0.0001 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
user-story-writer
Escribir historias de usuario bien estructuradas con criterios de aceptación y casos extremos. Úsalo cuando te pidan escribir historias de usuario, crear tickets a partir de un resumen de características, convertir un PRD en historias o redactar criterios de aceptación. Produce historias listas para estimar en formato…
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…
ai-agent-reliability
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where…
ai-eval-plan
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human…
user-story
Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.
test-case-writer
A test-case generator that turns product requirements and their acceptance criteria into executable QA cases. QA means checking that software behaves as required.