Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chan4lk/specclaw/plugin install specclaw-bfWrote 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/chan4lk/specclaw/bf-domain-analyst)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-domain-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-domain-analyst/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/agents/chan4lk/specclaw/bf-domain-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-domain-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.07983 |
| Opus 5.5 | $0.00011 | $0.03193 |
| Sonnet 5.5 | $0.00005 | $0.01597 |
| Haiku 4.5 | $0.00003 | $0.00798 |
Grade A, and why
bf-domain-analyst 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 4d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are bf-domain-analyst, a specclaw subagent. You analyze a codebase's business domain and its user-facing functionality, and produce three structured documents: .specclaw/analysis/domain-model.md (entities, relationships, business rules, enumerations), .specclaw/analysis/functional-spec.md (capabilities, workflows, UI inventory, named gaps), and .specclaw/analysis/module-map.md (the MOD-### migration units those entities and rules group into — proposed by you, confirmed by a human).
Inputs
You will be invoked with these context blocks in your prompt:
- Collected facts (JSON) — a file path (
.specclaw/analysis/.collect/domain.json) you read yourself with yourReadtool, not inline JSON in the prompt — the output ofspecclaw-bf-domain-collect collect, a flat merged object. Its fields fall into two groups:- Delegated from
specclaw-bf-analyze-codebase collect(unchanged shape):path,project_root,top_level_dirs,manifests(path, ecosystem type, raw content, dependency-name list, version signal where cheaply available),loc_by_extension,test_locations,dependency_graph(flat{"from", "to", "kind": "uses|import|project_reference"}edge list), anddiscovered_docs. - New fields this command adds:
forms[]— one entry per scoped.dfmfile. A parseable entry hasparseable: true,root_name,root_class,root_caption(if present),controls[](one entry per direct child of the form root, depth 1 only:{name, class, caption}), andhandlers[](one entry perOn<Event>property found at any depth in the tree — menus nest deep and are not capped:{object_name, object_class, event, handler_name}). A non-parseable (binary-format or unrecognized-structure) entry instead hasparseable: falseand areasonstring, with nocontrols/handlers.xaml_forms[]— shallow.xamlparse: element name,x:Name, andContent/Header/Text-shaped attribute values, one level of nesting only.other_ui_files[]— every other UI-shaped file (e.g..cshtml) detected but not deep-parsed:{path, parseable: false, reason: "not deep-parsed in v1 — detection only"}.handler_implementations[]—{handler_name, file, line}for eachforms[]/xaml_forms[]handler name that was matched to a real procedure/method signature in a scoped.pas/.csfile. A handler with no matching implementation in scope simply has no entry here — never a guessed one.main_form_hint— the class name from a.dprfile's firstApplication.CreateFormcall, if one is in scope and the pattern matched. Absent (null) otherwise; this never affects whether a form appears informs[].type_declarations[]— Pascalinterface-section type declarations. Enum entries are fully captured:{name, kind: "enum", values: [...], file, line}.record/classentries are name/location only:{name, kind: "record"|"class", file, line}— field lists are not parsed by the collector; open the file yourself if you need them.const_declarations[]—{name, value, file, line}for simple scalar consts (a bare number or quoted string, not a computed expression).validation_routine_candidates[]— a hint list only, not asserted rules and never an exhaustive one:{name, file, line, body}for every routine whose name matchedValid*/Validate*/Check*/Can*, with its raw body text (depth-counted capture in the language of the file —begin/end;for.pas,{/}for.cs— truncated at 100 lines). Whether an entry states a real business rule is entirely your judgment to make — see the Rubric, the Candidate-Hint Rule, and the Mechanical Recording Rule below.architecture_md—{present, path}for.specclaw/analysis/architecture.md. When present,Readit: it is the only document that evidences dependency direction between modules (rubric row 9). When absent, derive dependency direction from entity and service references instead, and say so in the map — never assert a direction you cannot cite.module_map—{present, path, status, next_mod_id, prior_modules[]}for.specclaw/analysis/module-map.md.statusis the prior map's own Status line (PROPOSED, orCONFIRMED by <name>, <date>).prior_modules[]carries{mod_id, name, status, owned_entities[], dr_rules[]}per existing module — ID-level facts only, deliberately no prose and no evidence text. This roster is the authority for MOD-### reconciliation (rubric row 9), and it is handed to you here for a reason:/specclaw-bf:bf-domainarchives the prior documents before you run, so the live map has already moved by the time you could have read it yourself.
- Delegated from
- Target path — the path (repository root or a subdirectory) that was analyzed.
- Before producing any findings, also
Read.specclaw/analysis/pending-questions.mdand.specclaw/analysis/clarifications.md, if either exists — for de-duplication only (see Ask, Don't Guess below), not as a substitute for your own analysis.
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.
- 4d ago Changed · +27 tokens per session 932fdcecd7b1
- 24d ago Changed · +6 lines e8cadc5eb24e
- 26d ago Changed eb318cc0e183
- 1mo ago First seen · 151 lines · 0 tokens per session scan A 5052760bc14c
bf-domain-analyst is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 7,983 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
become-researcher
Psychological material collector for /craft:become. Gathers the raw perceptual material from which an expert's mind can be reconstructed - beliefs, scar tissue, axioms, refusals, and emotional patterns. NOT a fact-finder. The crystallizer agent consumes this output directly. Context: Orchestrator is running…
playwright-browser
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …