Repository navigation
Conversation
📝 WalkthroughWalkthroughChangesThe activation documentation for BMM, core, and legacy shim skills now specifies direct TOML customization merging instead of runtime resolver scripts. Selected skills also define ordered config TOML merging, field extraction, and neutral defaults. Activation Resolution
Estimated code review effort: 3 (Moderate) | ~20 minutes Possibly related issues
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md (1)
23-31: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winReplace the impossible “If the script fails” branch.
The preceding sentence forbids executing scripts, so this fallback is contradictory and unreachable. Replace it with explicit TOML error handling: the base
customize.tomlis required and should fail activation if missing or invalid; optional team/user files may be skipped with a warning when absent or unreadable, matching the existing resolver behavior.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md` around lines 23 - 31, Replace the contradictory “If the script fails” fallback in the activation instructions with explicit TOML error handling: require the base customize.toml and fail activation when it is missing or invalid; skip absent or unreadable team and user override files with warnings, matching the existing resolver behavior. Apply this change in src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md:23-31, src/bmm-skills/3-solutioning/bmad-check-implementation-readiness/SKILL.md:52-60, src/bmm-skills/3-solutioning/bmad-create-epics-and-stories/SKILL.md:54-62, src/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.md:33-41, src/bmm-skills/4-implementation/bmad-agent-dev/SKILL.md:23-31, src/bmm-skills/4-implementation/bmad-checkpoint-preview/SKILL.md:23-31, src/bmm-skills/4-implementation/bmad-code-review/SKILL.md:24-32, src/bmm-skills/4-implementation/bmad-correct-course/SKILL.md:23-31, src/bmm-skills/4-implementation/bmad-create-story/SKILL.md:33-41, src/bmm-skills/4-implementation/bmad-dev-auto/SKILL.md:81-89, and src/bmm-skills/4-implementation/bmad-dev-story/SKILL.md:30-38.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/bmm-skills/1-analysis/bmad-agent-analyst/SKILL.md`:
- Around line 23-25: Remove the obsolete “If the script fails” fallback from the
activation instructions in src/bmm-skills/1-analysis/bmad-agent-analyst/SKILL.md
lines 23-25, src/bmm-skills/1-analysis/bmad-agent-tech-writer/SKILL.md lines
23-25, src/bmm-skills/1-analysis/bmad-document-project/SKILL.md lines 23-25,
src/bmm-skills/1-analysis/bmad-prfaq/SKILL.md lines 33-35,
src/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests/SKILL.md lines 23-25,
src/bmm-skills/4-implementation/bmad-retrospective/SKILL.md lines 39-41,
src/bmm-skills/4-implementation/bmad-sprint-planning/SKILL.md lines 23-25, and
src/bmm-skills/4-implementation/bmad-sprint-status/SKILL.md lines 23-25; if
retaining fallback behavior, rewrite each branch to handle only TOML read
failures while preserving data-only activation and never executing resolver
scripts.
- Line 23: Update the customization resolver documentation in the English,
French, and Vietnamese guides to describe direct TOML loading and merging during
activation instead of invoking resolve_customization.py. Revise examples and
fallback text to reflect the base customize.toml plus optional project and user
override files, without directing users to installer-owned scripts.
In `@src/bmm-skills/2-plan-workflows/bmad-agent-pm/SKILL.md`:
- Line 23: Remove the obsolete script-failure fallback blocks immediately
following the activation instructions in both
src/bmm-skills/2-plan-workflows/bmad-agent-pm/SKILL.md (Lines 25–31) and
src/bmm-skills/2-plan-workflows/bmad-agent-ux-designer/SKILL.md (Lines 25–31);
retain the direct-TOML resolution instructions and resolved agent values in each
activation section.
In `@src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md`:
- Around line 21-23: Update the relevant activation documentation under docs/ to
describe the TOML-based customization contract: read skill-root customize.toml
first, then optionally merge the project and user override files in order, with
scalar overrides, deep table merges, and the specified array handling.
Explicitly document that project scripts are not executed during activation and
that resolved agent values drive activation.
In `@src/bmm-skills/3-solutioning/bmad-architecture/SKILL.md`:
- Around line 53-54: The activation flow in bmad-architecture must defer
`{workflow.activation_steps_append}` until after merged configuration is
resolved and the user is greeted. Update the instructions around the workflow
activation steps so prepend hooks run first, config resolution and greeting
follow, and append hooks run last, matching the ordering used by the other
activation flows.
In `@src/core-skills/bmad-advanced-elicitation/SKILL.md`:
- Line 17: Document the activation contract in all six affected files:
src/core-skills/bmad-advanced-elicitation/SKILL.md:17-17 must describe direct
customization TOML merging; src/core-skills/bmad-brainstorming/SKILL.md:21-23
and src/core-skills/bmad-forge-idea/SKILL.md:25-27 and
src/core-skills/bmad-party-mode/SKILL.md:19-20 must describe direct
customization and core-config TOML merging;
src/core-skills/bmad-deep-recon/SKILL.md:40-41 must describe direct
customization/config merging and hook ordering; and
src/core-skills/bmad-review/SKILL.md:27-27 must describe direct customization
merging and forwarded activation behavior. State that activation reads and
merges the relevant TOML layers directly rather than executing resolver scripts.
In `@src/core-skills/bmad-deep-recon/SKILL.md`:
- Around line 40-41: Reorder activation so central configuration is fully
resolved before executing {workflow.activation_steps_append}. In the activation
flow described by items 1–2, resolve user_name, project_name, output_folder, and
related values first, then run the append hooks while preserving the existing
prepend-hook ordering.
---
Outside diff comments:
In `@src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md`:
- Around line 23-31: Replace the contradictory “If the script fails” fallback in
the activation instructions with explicit TOML error handling: require the base
customize.toml and fail activation when it is missing or invalid; skip absent or
unreadable team and user override files with warnings, matching the existing
resolver behavior. Apply this change in
src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md:23-31,
src/bmm-skills/3-solutioning/bmad-check-implementation-readiness/SKILL.md:52-60,
src/bmm-skills/3-solutioning/bmad-create-epics-and-stories/SKILL.md:54-62,
src/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.md:33-41,
src/bmm-skills/4-implementation/bmad-agent-dev/SKILL.md:23-31,
src/bmm-skills/4-implementation/bmad-checkpoint-preview/SKILL.md:23-31,
src/bmm-skills/4-implementation/bmad-code-review/SKILL.md:24-32,
src/bmm-skills/4-implementation/bmad-correct-course/SKILL.md:23-31,
src/bmm-skills/4-implementation/bmad-create-story/SKILL.md:33-41,
src/bmm-skills/4-implementation/bmad-dev-auto/SKILL.md:81-89, and
src/bmm-skills/4-implementation/bmad-dev-story/SKILL.md:30-38.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 0e0a44d8-a2e1-4fb8-b29f-684a840f8482
📒 Files selected for processing (39)
src/bmm-skills/1-analysis/bmad-agent-analyst/SKILL.mdsrc/bmm-skills/1-analysis/bmad-agent-tech-writer/SKILL.mdsrc/bmm-skills/1-analysis/bmad-document-project/SKILL.mdsrc/bmm-skills/1-analysis/bmad-prfaq/SKILL.mdsrc/bmm-skills/1-analysis/bmad-product-brief/SKILL.mdsrc/bmm-skills/2-plan-workflows/bmad-agent-pm/SKILL.mdsrc/bmm-skills/2-plan-workflows/bmad-agent-ux-designer/SKILL.mdsrc/bmm-skills/2-plan-workflows/bmad-prd/SKILL.mdsrc/bmm-skills/2-plan-workflows/bmad-spec/SKILL.mdsrc/bmm-skills/2-plan-workflows/bmad-ux/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-architecture/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-check-implementation-readiness/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-create-epics-and-stories/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.mdsrc/bmm-skills/4-implementation/bmad-agent-dev/SKILL.mdsrc/bmm-skills/4-implementation/bmad-checkpoint-preview/SKILL.mdsrc/bmm-skills/4-implementation/bmad-code-review/SKILL.mdsrc/bmm-skills/4-implementation/bmad-correct-course/SKILL.mdsrc/bmm-skills/4-implementation/bmad-create-story/SKILL.mdsrc/bmm-skills/4-implementation/bmad-dev-auto/SKILL.mdsrc/bmm-skills/4-implementation/bmad-dev-story/SKILL.mdsrc/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests/SKILL.mdsrc/bmm-skills/4-implementation/bmad-retrospective/SKILL.mdsrc/bmm-skills/4-implementation/bmad-sprint-planning/SKILL.mdsrc/bmm-skills/4-implementation/bmad-sprint-status/SKILL.mdsrc/bmm-skills/v6-shims/bmad-create-architecture/SKILL.mdsrc/bmm-skills/v6-shims/bmad-create-prd/SKILL.mdsrc/bmm-skills/v6-shims/bmad-domain-research/SKILL.mdsrc/bmm-skills/v6-shims/bmad-edit-prd/SKILL.mdsrc/bmm-skills/v6-shims/bmad-market-research/SKILL.mdsrc/bmm-skills/v6-shims/bmad-technical-research/SKILL.mdsrc/bmm-skills/v6-shims/bmad-validate-prd/SKILL.mdsrc/core-skills/bmad-advanced-elicitation/SKILL.mdsrc/core-skills/bmad-brainstorming/SKILL.mdsrc/core-skills/bmad-deep-recon/SKILL.mdsrc/core-skills/bmad-forge-idea/SKILL.mdsrc/core-skills/bmad-party-mode/SKILL.mdsrc/core-skills/bmad-review/SKILL.md
Contributor
Greptile SummaryThis PR replaces activation-time
Confidence Score: 3/5
|
| Filename | Overview |
|---|---|
| src/bmm-skills/agents/bmad-agent-analyst/SKILL.md | Step 1 now correctly prohibits script execution, but the immediately-following "If the script fails" block (lines 25–31) still describes the same TOML merge as a fallback for a script that was never supposed to run — creating a logical contradiction an LLM could misinterpret as permission to try the script first. |
| src/core-skills/bmad-party-mode/SKILL.md | On Activation steps 1–2 correctly prohibit resolver script execution; however, the Conventions section (line 13) still lists both resolve_config.py and resolve_customization.py as the canonical scripts for config/customization resolution without any "activation-only" carve-out, conflicting with the new instructions. |
| src/bmm-skills/plan/bmad-sprint-planning/SKILL.md | Not included in the PR changeset; On Activation step 1 still runs uv run … resolve_customization.py — the exact pattern this fix is supposed to eliminate. |
| src/bmm-skills/plan/bmad-architecture/SKILL.md | Both resolve_customization.py (step 1) and resolve_config.py (step 2) replaced with direct TOML-merge instructions; config layer description omits the specific four file names (a pre-existing omission also noted in the review thread for several other files). |
| src/bmm-skills/plan/bmad-spec/SKILL.md | Both resolver calls replaced with direct TOML-merge; the new config step 3 still doesn't name the four specific files (_bmad/config.toml, _bmad/config.user.toml, _bmad/custom/config.toml, _bmad/custom/config.user.toml), as already noted in the review thread. |
| src/bmm-skills/ship/bmad-retrospective/SKILL.md | Not included in the PR changeset; activation step 1 still executes uv run --no-cache resolve_customization.py, leaving the arbitrary-code-execution path open for this skill. |
| src/bmm-skills/plan/bmad-project-context/SKILL.md | Not in the PR; activation steps 1 and 2 both call resolver scripts (resolve_customization.py and resolve_config.py) — the only uncovered file with two activation-time resolver calls. |
| src/core-skills/bmad-brainstorming/SKILL.md | Both resolver calls replaced; the new step 3 config resolution follows the same underspecified "two base + two override" pattern as other files. |
| src/bmm-skills/v6-shims/bmad-sprint-status/SKILL.md | Not in the PR; On Activation step 1 still runs uv run resolve_customization.py. |
Flowchart
%%{init: {'theme': 'neutral'}}%%
flowchart TD
A[Skill Activation] --> B{PR Changed\nThis File?}
B -- Yes --> C[Direct TOML Merge]
B -- No --> D{Has Resolver\nCall in Activation?}
C --> E[Read skill-root/customize.toml]
E --> F[Merge _bmad/custom/skill-name.toml]
F --> G[Merge _bmad/custom/skill-name.user.toml]
G --> H[✅ Safe — no code execution]
D -- No --> I[✅ Not applicable]
D -- Yes --> J[⚠️ Still runs uv run resolve_customization.py\nor resolve_config.py]
J --> K[bmad-sprint-planning\nbmad-retrospective\nbmad-sprint-status\nbmad-project-context]
K --> L[❌ Arbitrary project code\nexecuted at startup]
Reviews (8): Last reviewed commit: "Merge branch 'main' into main" | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Contributor
Author
|
Conflict solved |
Contributor
Author
|
Ready to merge |
6 tasks
Collaborator
|
Thank you for raising this — the concern in #2624 (activation executing unverified project-local scripts) is real and worth tracking. Closing this PR in its current form: the conflict-resolution merge in early August dropped the core-skills coverage the original diff had, every edited file still carries the "if the script fails, resolve the block yourself" fallback that contradicts the new instruction, and the branch is conflicting with main again. More fundamentally, replacing the deterministic resolver scripts with in-chat TOML merging is a design change we are not taking right now — the v7 rework in flight will reshape how skills resolve config, and #2624 stays open as the record of the concern. — |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Updated BMAD skill activation instructions so they no longer execute
resolve_customization.pyorresolve_config.pyfrom{project-root}/_bmad/scriptsduring activation, and instead resolve customization/config by directly merging the documented TOML layers.Why
This removes the activation-time execution path for project-supplied resolver scripts, so
_bmad/stays data-only during activation and skill startup no longer trusts arbitrary code from the working tree. (#2624)How
resolve_customization.pycalls in affectedSKILL.mdfiles with explicit TOML merge instructions using base, team, and user customization layers.resolve_config.pycalls in affectedSKILL.mdfiles with direct four-layer config merge instructions.workflow.on_completeuntouched so the fix stays scoped to the reported issue.Testing
I did not add or run tests per your instruction. I did run
npm ci && npm run quality, but the repo’sdocs:buildstep fails on Windows by design because that pipeline explicitly does not support Windows.