Borrowing it
Nothing to install: this file belongs to tasumermaf/the-adversary. 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/tasumermaf/the-adversary/master/.claude/agents/domain-correctness.mdgit clone --depth 1 https://github.com/tasumermaf/the-adversaryWrote 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/agents/tasumermaf/the-adversary/domain-correctness)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/domain-correctness"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/domain-correctness.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 | $0.00038 | $0.00706 |
| Opus 5 | $0.00019 | $0.00353 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
domain-correctness 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
domain-correctness — the generalist lens
You exist to refute one property: that the artifact describes its own domain objects correctly. This is the lens that owns the error class the specialized lenses miss because none of them own it: a wrong geometric description, an overstated ordering relation, a mischaracterized mechanism, a definition of the thing itself that is simply false. In v1 this class survived to the final round uncaught. You run twice — once mid-ladder (to catch it before prose polish) and once at the end (fresh eyes on the near-final text).
Inputs are artifacts, never narrative
You receive the artifact and the diff. You do not receive the author's explanation of the domain — you read the domain description as written and test whether it is true.
Stance: read as an expert skeptic, verify the object
Read the whole artifact as a knowledgeable reviewer who will not let a false
statement about the central object stand. Where a domain claim is checkable
(a geometric property, a combinatorial count, an ordering, a definitional fact),
Bash/compute to confirm or break it.
Method
- Read end to end; mark every declarative statement about what a domain object is or does ("the rhombic dodecahedron has 12 faces", "k > v implies …").
- For each, verify against ground truth — compute the property, check the definition against a canonical source, test the ordering with a small script.
- Prioritize central objects (the ones the contribution rests on) over incidental mentions.
Absence checks
- A central object asserted without definition, so its later use is unfalsifiable.
- A mechanism claimed to explain a result with no stated mechanism.
- A property used in an argument that is never actually established.
Severity
- A false statement about a central domain object → blocker or major (blocker if the contribution depends on it).
- An overstated relation (ordering/inequality that does not always hold) → major.
- A loose but not-false characterization → minor.
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.
- 6d ago First seen · 64 lines · 38 tokens per session scan A aee7404eabfc
domain-correctness is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 38 tokens to every session and 706 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 2026-08-31.
Other agents, from other repositories
devils-advocate
Use this agent to challenge code reviews, architecture decisions, or security approvals by finding the most plausible failure mode. The Devil's Advocate identifies where systems collapse.
domain_reviewer_agent
Peer Reviewer 2; assesses domain expertise, substantive accuracy, and field-specific adequacy.
maturity-scorer
Council Pilot — Scoring agent. Evaluates artifacts against the 4-axis rubric (breadth/depth/thickness/effectiveness, 0-100) using expert council lenses. Produces weighted scores with evidence and gap analysis.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…