菜单
Print the ADR domain tree (parent → child via AFM-0020 parent-edge model) optionally filtered by domain prefix, via `adr-fmt --tree [DOMAIN]`. Use when the user wants to enumerate ADRs in a domain, see the architectural hierarchy, or mentions "adr-fmt --tree".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | adr-tree |
| description | Print the ADR domain tree (parent → child via AFM-0020 parent-edge model) optionally filtered by domain prefix, via `adr-fmt --tree [DOMAIN]`. Use when the user wants to enumerate ADRs in a domain, see the architectural hierarchy, or mentions "adr-fmt --tree". |
Wrapper around adr-fmt --tree [DOMAIN]. Renders the ADR corpus as
a tree using parent-edge relationships (AFM-0020). Without a filter,
prints all domains; with a domain prefix (e.g. AFM, SEC, CHE),
restricts to that domain's tree.
Domain prefix is upper-case, three letters, matching the ADR ID
prefix — e.g. AFM, SEC, GND, CHE, FLO, COM, PAR.
Lower-case domain paths (adr-fmt, security) are the directory
names, not the filter argument.
If the user gives a directory name, translate to the prefix:
| Directory | Prefix |
|---|---|
| adr-fmt | AFM |
| common | COM |
| ground | GND |
| genome | (check adr-fmt.toml) |
| pardosa | PAR |
| security | SEC |
| flow | FLO |
| cherry | CHE |
When in doubt, run unfiltered first and read the domain headers.
# All domains
cargo run -p adr-fmt --release -- --tree
# Single domain
cargo run -p adr-fmt --release -- --tree <PREFIX>
Output structure (per domain):
## <Domain Name> (<PREFIX>)
<ADR-ID> <Title> [<Tier>] <Status>
├─ <child-ADR-ID> ...
│ └─ <grandchild> ...
└─ ...
(<n> stale)
Tier letters: S (paradigm) > A > B > C > D (parameters), per
AFM-0011. Status is the MADR lifecycle state (Draft, Accepted,
Superseded, Deprecated).
The [also: References X, Supersedes Y] annotations on a row are
non-tree edges — useful context when assessing impact.
Domain(s): <PREFIX | ALL>
ADRs: <n> Stale: <n>
Top of tree:
<verbatim first 5–10 lines, preserving tree art>
Artefact: .ooda/tree-<prefix>-<ts>.md (if > ~40 lines)
For long trees, write the full output to .ooda/tree-...md and surface
only the roots + structure summary.
| User intent | Invocation |
|---|---|
| "List all ADRs about X-domain" | --tree <PREFIX> |
| "Show the architecture" | --tree (unfiltered) |
| "Find ADR for crate Y" | Map crate → domain via adr-fmt.toml, then --tree <PREFIX> |
| "Find stale ADRs" | Look at (N stale) footer; cross-ref with --refs |
[also: ...],
not as tree branches.Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Surface the architectural rules applicable to a specific crate via `adr-fmt --context <CRATE>`. Use when an agent (especially oracle, moltke, hopper) needs the binding constraints for code in a crate before deciding or editing, or when the user asks "what rules apply to crate X?"
Run `adr-fmt --lint` against the ADR corpus and triage diagnostics by namespace (T0xx template, L0xx links, S0xx supersedes/lifecycle, P0xx parser). Use when the user asks to lint ADRs, check ADR integrity, validate the corpus, or mentions "adr-fmt --lint".
List inbound References and Supersedes citations of a target ADR via `adr-fmt --refs <ADR_ID>`. Use when the user asks who references / supersedes / cites an ADR, wants to assess blast radius before changing an ADR, or mentions "adr-fmt --refs".