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 magnus919/hermes-profiles --skill sdd-verificationgit clone --depth 1 https://github.com/magnus919/hermes-profilesWrote 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/magnus919/hermes-profiles/sdd-verification)<a href="https://agentmods.dev/skills/magnus919/hermes-profiles/sdd-verification"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/sdd-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/magnus919/hermes-profiles/sdd-verification"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/sdd-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01398 |
| Opus 5 | $0.00024 | $0.00699 |
| Sonnet 5 | $0.00010 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
sdd-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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Verification
Validating that implementation output satisfies every acceptance criterion defined in the specification. This skill owns the Verify phase of the SDD pipeline — the final gate before delivery.
SDD Pipeline Position
SPECIFY → PLAN → TASKS → IMPLEMENT → [VERIFY]
↑
You are here
Verification is the phase that closes the loop. If specification is the question ("what should the system do?") and implementation is the answer ("this is what the system does"), verification is the judgment ("does the answer satisfy the question?").
Core Principle: Every AC Produces a Binary Verdict
An acceptance criterion that cannot produce a CLEAR PASS or CLEAR FAIL is not a well-defined AC. Verification exposes spec defects: if a criterion is ambiguous and cannot be tested, it is a spec bug, not an implementation failure. Verification findings thus flow in two directions — implementation failures (code doesn't meet the spec) and spec failures (the spec is untestable or ambiguous).
Artifact-Pyramid Output: VERIFICATION.md
Verification reports follow the artifact-pyramid structure:
| Layer | Content | File |
|---|---|---|
| L1 | Pass/fail summary — total ACs tested, pass count, fail count, compliance score, blocking verdict | 00-index.md (entry point) |
| L2 | Verification matrix — per-story or per-feature-area AC status grouped for navigation | Individual *.verification.md files |
| L3 | Individual failure dossiers — what failed, expected behavior (from spec), actual behavior (from implementation), evidence, severity | dossiers/ directory |
| SOURCES | Cross-reference from each AC back to its SPEC.md section | Footer of each file |
Loading Guidance
| Reference | When to load | File |
|---|---|---|
| Acceptance Criteria Verification | Before running verification — methodology for testing ACs that may not have dedicated test infrastructure | references/acceptance-criteria-verification.md |
| Spec-to-Test Mapping | When existing tests exist — how to map test coverage back to spec ACs and identify gaps | references/spec-to-test-mapping.md |
| Escalation Protocol | When an AC is ambiguous or an implementation finding needs escalation — what to do when verification can't produce a clean verdict | references/escalation-protocol.md |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 115 lines · 48 tokens per session scan A 220e54c4b47c
sdd-verification is a skill published in the GitHub repository magnus919/hermes-profiles (161 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,398 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.