diff --git a/plugins/compound-engineering/AGENTS.md b/plugins/compound-engineering/AGENTS.md index 967938274..78c749b00 100644 --- a/plugins/compound-engineering/AGENTS.md +++ b/plugins/compound-engineering/AGENTS.md @@ -144,6 +144,10 @@ Why: shell-heavy exploration causes avoidable permission prompts in sub-agent wo When a skill orchestrates sub-agents that need codebase reference material, prefer passing file paths over file contents. The sub-agent reads only what it needs. Content-passing is fine for small, static material consumed in full (e.g., a JSON schema under ~50 lines). +### Sub-Agent Permission Mode + +When dispatching sub-agents, **omit the `mode` parameter** on the Agent/Task tool call unless the skill explicitly needs a specific mode (e.g., `mode: "plan"` for plan-approval workflows). Passing `mode: "auto"` or any other value overrides the user's configured permission settings (e.g., `bypassPermissions` in their user-level config), which is never the intended behavior for routine subagent dispatch. Omitting `mode` lets the user's own `defaultMode` setting apply. + ### Quick Validation Command ```bash diff --git a/plugins/compound-engineering/skills/ce-compound-refresh/SKILL.md b/plugins/compound-engineering/skills/ce-compound-refresh/SKILL.md index 29a6bde26..608b3a452 100644 --- a/plugins/compound-engineering/skills/ce-compound-refresh/SKILL.md +++ b/plugins/compound-engineering/skills/ce-compound-refresh/SKILL.md @@ -270,7 +270,7 @@ Use subagents for context isolation when investigating multiple artifacts — no | **Parallel subagents** | 3+ truly independent artifacts with low overlap | | **Batched subagents** | Broad sweeps — narrow scope first, then investigate in batches | -**When spawning any subagent, include this instruction in its task prompt:** +**When spawning any subagent**, omit the `mode` parameter so the user's configured permission settings apply. Include this instruction in its task prompt: > Use dedicated file search and read tools (Glob, Grep, Read) for all investigation. Do NOT use shell commands (ls, find, cat, grep, test, bash) for file operations. This avoids permission prompts and is more reliable. > diff --git a/plugins/compound-engineering/skills/ce-ideate/SKILL.md b/plugins/compound-engineering/skills/ce-ideate/SKILL.md index 0fda229a1..d61b6589e 100644 --- a/plugins/compound-engineering/skills/ce-ideate/SKILL.md +++ b/plugins/compound-engineering/skills/ce-ideate/SKILL.md @@ -135,7 +135,7 @@ Do **not** do external research in v1. Generate the full candidate list before critiquing any idea. -Dispatch 3-4 parallel ideation sub-agents on the inherited model (do not tier down -- creative ideation needs the orchestrator's reasoning level). Each targets ~8-10 ideas (yielding ~30 raw ideas, ~20-25 after dedupe). Adjust per-agent targets when volume overrides apply (e.g., "100 ideas" raises it, "top 3" may lower the survivor count instead). +Dispatch 3-4 parallel ideation sub-agents on the inherited model (do not tier down -- creative ideation needs the orchestrator's reasoning level). Omit the `mode` parameter so the user's configured permission settings apply. Each targets ~8-10 ideas (yielding ~30 raw ideas, ~20-25 after dedupe). Adjust per-agent targets when volume overrides apply (e.g., "100 ideas" raises it, "top 3" may lower the survivor count instead). Give each sub-agent: the grounding summary, the focus hint, the per-agent volume target, and an instruction to generate raw candidates only (not critique). Each agent's first few ideas tend to be obvious -- push past them. Ground every idea in the Phase 1 scan. diff --git a/plugins/compound-engineering/skills/ce-plan/references/deepening-workflow.md b/plugins/compound-engineering/skills/ce-plan/references/deepening-workflow.md index 85ad6928f..823be1860 100644 --- a/plugins/compound-engineering/skills/ce-plan/references/deepening-workflow.md +++ b/plugins/compound-engineering/skills/ce-plan/references/deepening-workflow.md @@ -168,7 +168,7 @@ Artifact-backed mode uses a per-run scratch directory under `.context/compound-e ## 5.3.6 Run Targeted Research -Launch the selected agents in parallel using the execution mode chosen above. If the current platform does not support parallel dispatch, run them sequentially instead. +Launch the selected agents in parallel using the execution mode chosen above. If the current platform does not support parallel dispatch, run them sequentially instead. Omit the `mode` parameter when dispatching so the user's configured permission settings apply. Prefer local repo and institutional evidence first. Use external research only when the gap cannot be closed responsibly from repo context or already-cited sources. diff --git a/plugins/compound-engineering/skills/ce-review/SKILL.md b/plugins/compound-engineering/skills/ce-review/SKILL.md index a187aeaaa..8a31b3ed4 100644 --- a/plugins/compound-engineering/skills/ce-review/SKILL.md +++ b/plugins/compound-engineering/skills/ce-review/SKILL.md @@ -387,6 +387,8 @@ The orchestrator (this skill) stays on the default model because it handles inte #### Spawning +Omit the `mode` parameter when dispatching sub-agents so the user's configured permission settings apply. Do not pass `mode: "auto"`. + Spawn each selected persona reviewer as a parallel sub-agent using the subagent template included below. Each persona sub-agent receives: 1. Their persona file content (identity, failure modes, calibration, suppress conditions) diff --git a/plugins/compound-engineering/skills/ce-work-beta/SKILL.md b/plugins/compound-engineering/skills/ce-work-beta/SKILL.md index 8063763fb..9300b4d2b 100644 --- a/plugins/compound-engineering/skills/ce-work-beta/SKILL.md +++ b/plugins/compound-engineering/skills/ce-work-beta/SKILL.md @@ -140,6 +140,8 @@ Determine how to proceed based on what was provided in ``. - Any resolved deferred questions relevant to that unit - Instruction to check whether the unit's test scenarios cover all applicable categories (happy paths, edge cases, error paths, integration) and supplement gaps before writing tests + **Permission mode:** Omit the `mode` parameter when dispatching subagents so the user's configured permission settings apply. Do not pass `mode: "auto"` — it overrides user-level settings like `bypassPermissions`. + After each subagent completes, update the plan checkboxes and task list before dispatching the next dependent unit. For genuinely large plans needing persistent inter-agent communication (agents challenging each other's approaches, shared coordination across 10+ tasks), see Swarm Mode below which uses Agent Teams. diff --git a/plugins/compound-engineering/skills/ce-work/SKILL.md b/plugins/compound-engineering/skills/ce-work/SKILL.md index 98a7256df..4f4df1ae6 100644 --- a/plugins/compound-engineering/skills/ce-work/SKILL.md +++ b/plugins/compound-engineering/skills/ce-work/SKILL.md @@ -139,6 +139,8 @@ Determine how to proceed based on what was provided in ``. - Any resolved deferred questions relevant to that unit - Instruction to check whether the unit's test scenarios cover all applicable categories (happy paths, edge cases, error paths, integration) and supplement gaps before writing tests + **Permission mode:** Omit the `mode` parameter when dispatching subagents so the user's configured permission settings apply. Do not pass `mode: "auto"` — it overrides user-level settings like `bypassPermissions`. + After each subagent completes, update the plan checkboxes and task list before dispatching the next dependent unit. For genuinely large plans needing persistent inter-agent communication (agents challenging each other's approaches, shared coordination across 10+ tasks), see Swarm Mode below which uses Agent Teams. diff --git a/plugins/compound-engineering/skills/document-review/SKILL.md b/plugins/compound-engineering/skills/document-review/SKILL.md index 13eec7c1a..1f81d7709 100644 --- a/plugins/compound-engineering/skills/document-review/SKILL.md +++ b/plugins/compound-engineering/skills/document-review/SKILL.md @@ -115,7 +115,7 @@ Add activated conditional personas: ### Dispatch -Dispatch all agents in **parallel** using the platform's task/agent tool (e.g., Agent tool in Claude Code, spawn in Codex). Each agent receives the prompt built from the subagent template included below with these variables filled: +Dispatch all agents in **parallel** using the platform's task/agent tool (e.g., Agent tool in Claude Code, spawn in Codex). Omit the `mode` parameter so the user's configured permission settings apply. Each agent receives the prompt built from the subagent template included below with these variables filled: | Variable | Value | |----------|-------| diff --git a/plugins/compound-engineering/skills/git-commit-push-pr/SKILL.md b/plugins/compound-engineering/skills/git-commit-push-pr/SKILL.md index c3fec5083..e709852bd 100644 --- a/plugins/compound-engineering/skills/git-commit-push-pr/SKILL.md +++ b/plugins/compound-engineering/skills/git-commit-push-pr/SKILL.md @@ -311,25 +311,12 @@ When referencing actual GitHub issues or PRs, use the full format: `org/repo#123 Append a badge footer to the PR description, separated by a `---` rule. Do not add one if the description already contains a Compound Engineering badge (e.g., added by another skill like ce-work). -**Plugin version (pre-resolved):** !`jq -r .version "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json"` - -If the line above resolved to a semantic version (e.g., `2.42.0`), use it as `[VERSION]` in the versioned badge below. Otherwise (empty, a literal command string, or an error), use the versionless badge. Do not attempt to resolve the version at runtime. - -**Versioned badge** (when version resolved above): - -```markdown ---- - -[![Compound Engineering v[VERSION]](https://img.shields.io/badge/Compound_Engineering-v[VERSION]-6366f1)](https://github.com/EveryInc/compound-engineering-plugin) -🤖 Generated with [MODEL] ([CONTEXT] context, [THINKING]) via [HARNESS](HARNESS_URL) -``` - -**Versionless badge** (when version is not available): +**Badge:** ```markdown --- -[![Compound Engineering](https://img.shields.io/badge/Compound_Engineering-6366f1)](https://github.com/EveryInc/compound-engineering-plugin) +[![Compound Engineering](https://img.shields.io/badge/Built_with-Compound_Engineering-6366f1)](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with [MODEL] ([CONTEXT] context, [THINKING]) via [HARNESS](HARNESS_URL) ``` @@ -359,7 +346,7 @@ EOF )" ``` -Use the versioned or versionless badge line resolved in the Compound Engineering badge section above. +Use the badge from the Compound Engineering badge section above. Keep the PR title under 72 characters. The title follows the same convention as commit messages (Step 2). diff --git a/plugins/compound-engineering/skills/orchestrating-swarms/SKILL.md b/plugins/compound-engineering/skills/orchestrating-swarms/SKILL.md index 94488286c..7b3df6b4f 100644 --- a/plugins/compound-engineering/skills/orchestrating-swarms/SKILL.md +++ b/plugins/compound-engineering/skills/orchestrating-swarms/SKILL.md @@ -194,6 +194,8 @@ Task({ - No team membership required - Best for: searches, analysis, focused research +**Permission mode:** Omit the `mode` parameter unless you need a specific mode like `mode: "plan"`. Passing `mode: "auto"` overrides the user's configured permission settings (e.g., `bypassPermissions`). Omitting it lets the user's own `defaultMode` apply. + ### Method 2: Task Tool + team_name + name (Teammates) Use Task with `team_name` and `name` to **spawn persistent teammates**: