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 agentmods add agents/h0x91b/dev-3.0/domaingit clone --depth 1 https://github.com/h0x91b/dev-3.0What 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 | $0.00000 | $0.00589 |
| Opus 5 | $0.00000 | $0.00295 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
domain 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 3d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Docs
How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.
Before exploring, read these
AGENTS.mdat the repo root — this repo's primary domain/architecture doc and coding conventions. There is no separateCONTEXT.md;CLAUDE.mdis a symlink toAGENTS.md. Also skimconcept.md(product concept + status),DESIGN.md(design system), anddocs/ux/PRODUCT_UX_BIBLE.md(UX placement) when the work touches product concept, visual design, or UX.decisions/— architectural decision records live here asdecisions/YYYY/MM/DD/slug.md, NOT underdocs/adr/(decisions/README.mdmaps the pre-2026-08-06NNN-slug.mdnames to their new paths). Read the ones that touch the area you're about to work in.
If a referenced file doesn't exist, proceed silently — don't flag its absence or suggest creating it upfront. The /domain-modeling skill creates domain docs lazily when terms or decisions actually get resolved. New decision records are named decisions/YYYY/MM/DD/slug.md — never numbered, see AGENTS.md § Decision records — with the required sections (Context / Investigation / Decision / Risks / Alternatives).
File structure (single-context)
/
├── AGENTS.md ← primary domain + conventions doc (CLAUDE.md → symlink)
├── concept.md ← product concept + implementation status
├── DESIGN.md ← design system
├── docs/ux/ ← UX manifest (PRODUCT_UX_BIBLE.md, ux-architecture.yaml)
├── decisions/ ← ADRs: YYYY/MM/DD/slug.md
└── src/
Use the project's vocabulary
When your output names a domain concept (a task title, a refactor proposal, a hypothesis, a test name), use the terms as they appear in AGENTS.md and the existing code (e.g. "worktree", "task", "project", "surface", "design token", "push message"). Don't drift to synonyms the project doesn't use.
If the concept you need isn't documented yet, that's a signal — either you're inventing language the project doesn't use (reconsider) or there's a real gap (note it for /domain-modeling).
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.
- 3d ago First seen · 35 lines · 0 tokens per session scan A 5edeca4ced05
domain is an agent published in the GitHub repository h0x91b/dev-3.0 (248 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 589 tokens. 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 agents, from other repositories
ai_slop_reviewer
Expert code auditor that detects AI-generated code quality defects, hallucinated patterns, and structural anti-patterns across any codebase.
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…
ap-framework-generator
L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…
ap-scoper
L3 useful-first roadmap author or complementary scout - proves capability when needed, inspects the real repository, and contributes to one executable ROADMAP.md without spawning.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.