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 darellchua2/opencode-config-template --skill verification-loop-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/verification-loop-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/verification-loop-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/verification-loop-skill.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 | $0.00022 | $0.02604 |
| Opus 5 | $0.00011 | $0.01302 |
| Sonnet 5 | $0.00004 | $0.00521 |
| Haiku 4.5 | $0.00002 | $0.00260 |
Grade C, and why
verification-loop-skill scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
9. **Iteration safety**: bounded-by-default (`Iterations: 25`); safety blocks `.env`, `node_modules/`, `rm -rf`, `git push --force`. See `autoresearch-core-skill/references/iteration-safety.md`. How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I provide continuous verification of implementations against defined requirements throughout the development cycle:
- Checkpoint Creation: Define verification checkpoints at key stages of implementation
- Requirement Tracking: Map each requirement to verifiable conditions
- Automated Verification: Check implementations against acceptance criteria automatically
- Regression Detection: Verify that new changes don't break existing functionality
- Progress Reporting: Track verification status across all requirements over time
When to use me
Use this skill when:
- You want to verify implementation against acceptance criteria before committing
- You're working on a feature with clear requirements and want continuous validation
- You need to ensure no requirements are missed during implementation
- You want to catch regressions as soon as they happen
- You're doing TDD/BDD and want structured verification beyond unit tests
Trigger phrases:
- "verify implementation"
- "check against requirements"
- "run verification"
- "validate against criteria"
- "checkpoint"
Core Workflow
Step 1: Define Verification Scope
Establish what needs to be verified:
## Verification Scope
### Source of Truth
- Issue/PLAN file: [reference]
- Acceptance criteria: [list]
- Requirements: [list]
### Files in Scope
| File | Purpose | Criteria Covered |
|------|---------|-----------------|
| src/auth/login.ts | Login handler | AC-1, AC-2 |
| src/auth/session.ts | Session management | AC-3, AC-4 |
| tests/auth.test.ts | Test coverage | AC-5 |
### Verification Levels
1. **Syntax** — Code compiles/types correctly
2. **Functional** — Code does what it should
3. **Integration** — Code works with other components
4. **Acceptance** — Code meets all acceptance criteria
5. **Non-regression** — Existing features still work
Step 2: Create Verification Checkpoints
Define checkpoints aligned with implementation phases:
## Checkpoints
### Checkpoint 1: Structure
- [ ] All required files exist
- [ ] File structure follows conventions
- [ ] Types/interfaces defined correctly
- [ ] No syntax errors
### Checkpoint 2: Core Logic
- [ ] Main functionality implemented
- [ ] Edge cases handled
- [ ] Error paths covered
- [ ] Input validation present
### Checkpoint 3: Tests
- [ ] Unit tests written
- [ ] Integration tests written (if applicable)
- [ ] Edge case tests present
- [ ] All tests passing
### Checkpoint 4: Acceptance
- [ ] AC-1: [description] — verified
- [ ] AC-2: [description] — verified
- [ ] AC-3: [description] — verified
### Checkpoint 5: Non-Regression
- [ ] Existing tests still pass
- [ ] No new lint errors
- [ ] No type errors
- [ ] Build succeeds
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.
- 4d ago First seen · 310 lines · 22 tokens per session scan C 6866c9d5d3ed
verification-loop-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,604 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.