diff --git a/.agents/skills/kiro-spec-batch/SKILL.md b/.agents/skills/kiro-spec-batch/SKILL.md index 804ed7a..f322f8b 100644 --- a/.agents/skills/kiro-spec-batch/SKILL.md +++ b/.agents/skills/kiro-spec-batch/SKILL.md @@ -65,10 +65,10 @@ Create a complete specification for feature "{feature-name}". 1. Read the brief at .kiro/specs/{feature-name}/brief.md for feature context 2. Read the roadmap at .kiro/steering/roadmap.md for project context 3. Execute the full spec pipeline. For each phase, read the corresponding skill's SKILL.md for complete instructions (templates, rules, review gates): - a. Initialize: Read .agent/skills/kiro-spec-init/SKILL.md, then create spec.json and requirements.md - b. Generate requirements: Read .agent/skills/kiro-spec-requirements/SKILL.md, then follow its steps - c. Generate design: Read .agent/skills/kiro-spec-design/SKILL.md, then follow its steps - d. Generate tasks: Read .agent/skills/kiro-spec-tasks/SKILL.md, then follow its steps + a. Initialize: Read .agents/skills/kiro-spec-init/SKILL.md, then create spec.json and requirements.md + b. Generate requirements: Read .agents/skills/kiro-spec-requirements/SKILL.md, then follow its steps + c. Generate design: Read .agents/skills/kiro-spec-design/SKILL.md, then follow its steps + d. Generate tasks: Read .agents/skills/kiro-spec-tasks/SKILL.md, then follow its steps 4. Set all approvals to true in spec.json (auto-approve mode, equivalent of -y flag) 5. Report completion with file list and task count ``` diff --git a/.kiro/specs/pre-push-safety-net/implementation-group-4.md b/.kiro/specs/pre-push-safety-net/implementation-group-4.md index beff655..63399bf 100644 --- a/.kiro/specs/pre-push-safety-net/implementation-group-4.md +++ b/.kiro/specs/pre-push-safety-net/implementation-group-4.md @@ -67,7 +67,7 @@ real capability; task 8.3 still owns actual eligibility. Task 4.2 brings progres ## Task 4.3 verification The agent service rejected the task 4.3 dispatch with `agent thread limit reached`. -The [kiro-impl skill](../../../.agent/skills/kiro-impl/SKILL.md) explicitly provides: +The [kiro-impl skill](../../../.agents/skills/kiro-impl/SKILL.md) explicitly provides: “If multi-agent is not available, fall back to manual mode execution for all tasks.” Implementation, review and completion checks therefore ran in the main context. This is a manual review record, not an independent-review claim. diff --git a/.kiro/specs/pre-push-safety-net/implementation-group-5.md b/.kiro/specs/pre-push-safety-net/implementation-group-5.md index 6d5eb24..28c69a8 100644 --- a/.kiro/specs/pre-push-safety-net/implementation-group-5.md +++ b/.kiro/specs/pre-push-safety-net/implementation-group-5.md @@ -7,7 +7,7 @@ Real capability eligibility and rollout readiness remain unproven. ## Execution and review mode Fresh implementer dispatch for 5.1 returned `agent thread limit reached`. -The [Kiro implementation skill](../../../.agent/skills/kiro-impl/SKILL.md) explicitly +The [Kiro implementation skill](../../../.agents/skills/kiro-impl/SKILL.md) explicitly states: “If multi-agent is not available, fall back to manual mode execution for all tasks.” Its manual review rule permits review in the main context when a fresh reviewer is unavailable. This run therefore uses manual implementation and adversarial review, not independent review. diff --git a/AGENTS.md b/AGENTS.md index fa568fb..55efa4f 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -46,7 +46,7 @@ Project memory keeps persistent guidance (steering, specs notes, component docs) - Progress check: `/kiro-spec-status {feature}` (use anytime) ## Skills Structure -Skills are located in `.agent/skills/kiro-*/SKILL.md` (moved from `.opencode/skills` on 2026-10-02; point OpenCode at this path) +Skills are located in `.agents/skills/kiro-*/SKILL.md` (moved from `.opencode/skills` on 2026-10-02; OpenCode searches `.agents/skills` by default) - Each skill is a directory with a `SKILL.md` file - Use `/skills` to inspect currently available skills - Invoke a skill directly with `/kiro-` diff --git a/README.md b/README.md index 19d8d9c..2ad7a63 100644 --- a/README.md +++ b/README.md @@ -232,7 +232,7 @@ numbers: [docs/decision-engine.md](docs/decision-engine.md). ## Agent integrations An agent that can run shell commands needs nothing but the CLI. For -[OpenCode](https://opencode.ai) there are optional project skills in `.agent/skills/`: +[OpenCode](https://opencode.ai) there are optional project skills in `.agents/skills/`: `openultrasast-scan`, `openultrasast-triage` and `openultrasast-fix-audit`. `ousast mcp` runs a narrow MCP server over stdio (newline-delimited JSON-RPC) with ten tools: diff --git a/src/openultrasast/provenance.py b/src/openultrasast/provenance.py index a1c1d21..15604e5 100644 --- a/src/openultrasast/provenance.py +++ b/src/openultrasast/provenance.py @@ -30,7 +30,7 @@ _AGENT_PATHS = ( ".jules", ".kiro", ".opencode", - ".agent", + ".agents", ) _MARKERS = ( ("Generated with Claude Code", "marker:claude-code"), diff --git a/tests/test_agent_skills.py b/tests/test_agent_skills.py index faf016b..25840d5 100644 --- a/tests/test_agent_skills.py +++ b/tests/test_agent_skills.py @@ -2,7 +2,7 @@ from pathlib import Path def test_project_agent_skills_have_required_frontmatter() -> None: - skills_root = Path(".agent/skills") + skills_root = Path(".agents/skills") # Scope to the project's own skills; third-party tooling (e.g. kiro-*) lives # alongside them and uses a different frontmatter convention. skill_files = sorted(skills_root.glob("openultrasast-*/SKILL.md"))