baf54250a9
Group F — manifest, capability, role, and assembler cleanup (post-audit 2026-05-02).
Dangling handoff targets stripped:
- validator.toml: removed handoffs to physics-deriver, patent-compliance
- code-implementer.toml: removed physics-deriver handoff
- architect.toml: removed physics-deriver
- ml-implementer.toml: removed physics-deriver, fixed "multi-node multi-node" typo
- ml-researcher.toml: removed physics-deriver, patent-researcher
- researcher.toml: removed patent-researcher
None of those manifest files exist in _manifests/. Comments added explaining
the removal date for future re-authoring.
Validator extension (_assembler):
- src/validator.rs: extended validate() with check_handoff_targets — every
[[handoff]].target must point to existing _manifests/<name>.toml.
Future dangling handoffs blocked at validate time.
- src/validator_tests.rs (new, 133 LOC): unit tests for handoff-target check.
- tests/fixtures/_manifests/: added valid stubs for previously-missing manifests
(architect, critic, security-auditor, validator,
ml-implementer, ml-researcher, infra-implementer)
so existing fixtures pass the new validator gate.
- tests/snapshots/: insta snapshots updated for researcher + code-implementer.
Atomar manifest fill-out (replaced stock copy-paste with domain-specific):
- code-implementer-typescript: Drizzle/Zod/Next.js semantics
- code-implementer-go: mesh networking, embedded servers
- code-implementer-swift: SwiftUI, SPM, macOS menubar
- code-implementer-python: RULE 0.2 exception language
- code-implementer-flutter: Riverpod, Clean Architecture
- infra-implementer-cicd/iac/container/secrets: tool-specific bans + scopes
- researcher-web/code: output_extra_fields fixed (was code-implementer copy-paste
"Largest file LOC", "Tests pass count" — now sources cited /
evidence grade / gaps section)
Capability schema completeness:
- policy/no-git-ops + quality/cargo-check-green: added stage = "runtime"
- 8 capabilities: added explicit parents = [] (was missing/inconsistent)
Role schema:
- _roles/auditor.toml + merger.toml: added [taxonomy] + [lineage] (was missing)
- _roles/explorer.toml: added comment that "Explore" is the canonical Claude Code
subagent type (case-sensitive)
Reference path cleanup (manifest references):
- critic.toml: ~/.claude/skills/architecture-rules/... -> path:user-skills/...
- researcher.toml: stripped ~/.claude/agents/validator.md (machine-local)
Misc:
- frontend-validator.toml: renumbered duplicate step 6 -> step 7
kei-registry test fixture suppression:
- tests/fixtures/{atom-sample,fake-kit,mini-kit}/.kei-registry-ignore (3 new files)
- DNA-INDEX.md was inflating atom count by ~10% from test fixture rows; ignore-file
hooks ready, kei-registry walker implementation is a follow-up.
Tests: 59 passed; 0 failed; 1 ignored (pre-existing #[ignore]). cargo check clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
59 lines
1.8 KiB
TOML
59 lines
1.8 KiB
TOML
# Atomar agent — auto-generated 2026-04-29 (RULE ZERO decomposition).
|
|
# 1 cube = 1 responsibility. Edit this manifest, not the .md.
|
|
|
|
name = "researcher-code"
|
|
description = "Codebase research specialist. Glob / Grep / Read only. E1-E6 grading."
|
|
tools = ["Glob", "Grep", "Read"]
|
|
model = "sonnet"
|
|
substrate_role = "read-only"
|
|
|
|
role = """
|
|
You do codebase-only research — find symbols, trace dependencies, identify owners (git blame), surface analogues. Evidence-Graded findings tied to file:line.
|
|
"""
|
|
|
|
blocks = [
|
|
"baseline",
|
|
"evidence-grading",
|
|
"memory-protocol",
|
|
]
|
|
|
|
domain_in = [
|
|
"Symbol discovery — Grep for function/type/constant definitions across the repo",
|
|
"Dependency tracing — who imports X, what does X import (caller/callee graph via Grep)",
|
|
"Ownership mapping — identify the canonical SSoT file for a type or route",
|
|
"Analogue search — find existing implementations before proposing new code",
|
|
"Constructor-Pattern audit — identify files >200 LOC or functions >30 LOC",
|
|
]
|
|
forbidden_domain = [
|
|
"Web research — hand off to researcher-web",
|
|
"Editing or writing code (read-only agent — no Edit / Write)",
|
|
"Whole-file dumps when Grep + targeted Read suffices",
|
|
"Fabricating file paths, function names, or line numbers",
|
|
]
|
|
output_extra_fields = [
|
|
"Sources cited (≥2 for load-bearing)",
|
|
"Evidence grade per claim",
|
|
"Gaps section present",
|
|
]
|
|
|
|
[[handoff]]
|
|
target = "validator"
|
|
trigger = "general fact-check fallback"
|
|
[references]
|
|
extra = [
|
|
"path:user-rules/code-style.md",
|
|
"path:user-rules/karpathy-behavioral.md",
|
|
]
|
|
|
|
[taxonomy]
|
|
kingdom = "manifest"
|
|
mechanism = "compose"
|
|
domain = "agent"
|
|
layer = "agent-substrate"
|
|
stage = "design-time"
|
|
stability = "stable"
|
|
language = "toml"
|
|
|
|
[lineage]
|
|
creator = "ag-orchestrator-human"
|
|
created = "2026-04-29"
|