Borrowing it
Nothing to install: this file belongs to PedroMosquera/squadai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/skills/sdd/sdd-verify/SKILL.mdgit clone --depth 1 https://github.com/PedroMosquera/squadaiWrote 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/pedromosquera/squadai/sdd-verify)<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-verify"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-verify/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/pedromosquera/squadai/sdd-verify"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-verify.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 | $0.00012 | $0.00668 |
| Opus 5 | $0.00006 | $0.00334 |
| Sonnet 5 | $0.00002 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
sdd-verify 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 9d 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.
What it actually says
SDD Verify Skill
Verify that the implementation matches the specification exactly. This is the final phase of the SDD pipeline — a systematic compliance check.
Steps
-
Set up the verification matrix: Create a checklist from the spec.
- List every interface contract from the spec
- List every success criterion
- List every edge case behavior
- List every non-functional requirement
-
Verify interface contracts: Check each function signature and behavior.
- Does the function exist with the correct signature?
- Does it return the correct types?
- Does it return the correct error types as specified?
- Are all side effects present?
- Are all invariants maintained?
-
Verify success criteria: Test each acceptance criterion.
- Write a test for each "Given/When/Then" in the spec if not already present
- Run the tests — each must pass
- If a criterion has no test, flag it as untested
-
Verify edge case behavior: Test the edge case table.
- For each row in the spec's Edge Case Behavior table, confirm the implementation produces the specified behavior
- If any edge case is not tested, write a test and run it
-
Verify non-functional requirements: Check constraints.
- Performance: run a benchmark if latency/throughput was specified
- Security: verify input validation for all untrusted inputs
- Reliability: check retry and timeout behavior if specified
-
Identify deviations: Flag any mismatch between spec and implementation.
- Omission: spec item not implemented
- Addition: behavior not in spec was added
- Deviation: behavior differs from what spec says
- Ambiguity: spec is unclear; implementation made an assumption
-
Produce the verification report: Summarize findings for the orchestrator.
Output Format
## Verification Report: <feature name>
### Interface Contracts
| Contract | Status | Notes |
|----------|--------|-------|
| FunctionName signature | ✓ PASS | |
| FunctionName error types | ✓ PASS | |
| SideEffect X | ✗ FAIL | Missing in implementation |
### Success Criteria
| Criterion | Test | Status |
|-----------|------|--------|
| Given X, when Y, then Z | TestFunctionName_Z | ✓ PASS |
### Edge Cases
| Condition | Expected | Actual | Status |
|-----------|----------|--------|--------|
| empty input | return ErrEmpty | returns nil | ✗ FAIL |
### Non-Functional Requirements
| Requirement | Verified By | Status |
|-------------|-------------|--------|
| latency < 100ms | BenchmarkFunctionName | ✓ PASS |
### Deviations
1. **Omission**: <spec item> not implemented. Severity: blocking/non-blocking.
2. **Addition**: <behavior> not in spec. Should be removed or spec updated.
### Verdict
PASS / FAIL — <summary>
### Required Actions Before Merge
1. <action>
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.
- 9d ago First seen · 86 lines · 12 tokens per session scan A 7d8f53d1c772
sdd-verify is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 668 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
argot-check
Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…
quality-gates
Expert knowledge in quality assurance gates, code quality standards, and automated checks. Use when enforcing quality standards.