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 pproenca/dot-skills --skill adversarial-dddgit clone --depth 1 https://github.com/pproenca/dot-skillsWrote 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/pproenca/dot-skills/adversarial-ddd)<a href="https://agentmods.dev/skills/pproenca/dot-skills/adversarial-ddd"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/adversarial-ddd.svg" alt="Measured on agentmods" 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 | $0.00196 | $0.01740 |
| Opus 5 | $0.00098 | $0.00870 |
| Sonnet 5 | $0.00039 | $0.00348 |
| Haiku 4.5 | $0.00020 | $0.00174 |
Grade A, and why
adversarial-ddd 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial DDD Gate
A domain-driven design and ubiquitous-language gate for any codebase — a pass/fail gate: a single blind reviewer subagent judges the work against this gate's rules with an adversarial mandate, and the work passes only when every rule is PASS or N/A. This skill renders verdicts; it never fixes the work.
The gate's engine is the glossary lifecycle: once a target contains domain concepts, a recorded ubiquitous language (a glossary) must exist — its absence is a FAIL whose fix list names the exact file to create and the terms it must define. Run the gate on any project and the first verdict forces the vocabulary into existence; every later run holds the code, tests, docs, and customer-facing copy to it and keeps it well-sized. That is how one skill produces a common, well-understood vocabulary across many projects, exactly as DDD prescribes.
When to Apply
- Domain code is about to merge and needs an objective PASS/FAIL on ubiquitous-language and domain-model quality, not advisory feedback.
- A project is being started or adopted and you want the shared vocabulary forced into existence — the first run's fix list is the glossary's initial contents.
- An agent (Claude, Codex) authored the code and you want an independent check on its known defaults:
*Manager/*Helpertypes,setStatus()transitions, anemic entities, vendor types absorbed into the model. - A DSL, fluent builder, or declarative spec format is being introduced and its surface needs judging as a domain-vocabulary artifact.
- A periodic audit — the codebase, docs, and stakeholder-facing surfaces have drifted and you want the divergences named with locations.
Do not apply to targets with no domain concepts — pure infrastructure, build tooling, generic libraries (the reviewer prompt's precondition aborts with "GATE NOT APPLICABLE"). Do not apply when the user wants explanations or refactoring rather than a verdict. Rules whose prerequisite structure is absent (no identifiable contexts, no DSL, no glossary yet for the conformance rules) go N/A, not FAIL — except the two absence rules (gloss-language-recorded, dsl-deterministic-validator-exists), where the missing artifact is itself the FAIL.
What ships with it
25 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.
- assets/templates/verdict.md 1.6 KB
- gotchas.md 2.7 KB
- metadata.json 1.4 KB
- references/_sections.md 2.5 KB
- references/ctx-domain-free-of-infrastructure.md 2.4 KB
- references/ctx-no-foreign-model-reach.md 2.4 KB
- references/ctx-one-writer-per-model.md 2.1 KB
- references/ctx-translate-external-models.md 2.5 KB
- references/dsl-deterministic-validator-exists.md 2.4 KB
- references/dsl-illegal-statements-unconstructible.md 2.6 KB
- references/dsl-semantic-model-separate-from-syntax.md 2.5 KB
- references/gloss-code-conforms.md 2.8 KB
- references/gloss-definitions-carry-meaning.md 2.3 KB
- references/gloss-language-recorded.md 2.8 KB
- references/gloss-terms-live.md 2.3 KB
- references/lang-code-docs-tests-one-vocabulary.md 2.2 KB
- references/lang-no-generic-names-in-domain.md 2.5 KB
- references/lang-one-meaning-per-name.md 2.3 KB
- references/lang-one-name-per-concept.md 2.5 KB
- references/lang-transitions-named-as-operations.md 2.3 KB
- references/model-domain-types-over-primitives.md 2.3 KB
- references/model-named-states-over-flag-piles.md 2.5 KB
- references/model-rules-live-with-the-model.md 2.3 KB
- references/model-valid-on-construction.md 2.4 KB
- references/reviewer-prompt.md 5.9 KB
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.
- 8d ago First seen · 63 lines · 196 tokens per session scan A 3c9e2bf03cef
adversarial-ddd is a skill published in the GitHub repository pproenca/dot-skills (203 stars, last pushed 23d ago), licensed MIT. It adds 196 tokens to every session and 1,740 once invoked, about $0.0010 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…