Add step enforcement system to prevent common LLM workflow execution issues:
- Step skipping (LLMs optimizing for speed)
- Missing Task agent spawns (direct execution instead of delegation)
- Proceeding without evidence of completion
- Skipping quality gates
New files:
- step-enforcement.xml: Verification gates with evidence requirements
- workflow-executor.agent.yaml: Disciplined executor with zero improvisation
Changes:
- workflow.xml: Add optional enforcement hooks (backwards compatible)
- module-help.csv: Register new task and agent
Activation: Set enforcement.enabled: true in workflow.yaml
This is opt-in - existing workflows work unchanged.
* fix: correct malformed XML syntax and remove hardcoded path
- Fix missing opening quote in activation-steps.txt: `n={HELP_STEP}"` → `n="{HELP_STEP}"`
- Remove spurious hyphen: `-Let` → `Let`
- Replace hardcoded `/Users/brianmadison/...` path with relative path
Fixes#1435
* fix: add missing HELP_STEP placeholder replacement
The activation-steps.txt template includes a {HELP_STEP} placeholder,
but activation-builder.js never calculated or replaced it. This caused
the literal string "{HELP_STEP}" to appear in compiled agent files.
Added helpStep calculation between menuStep and haltStep, and adjusted
subsequent step numbers accordingly.
Fixes#1441
* Update src/bmm/workflows/2-plan-workflows/create-prd/validation-report-prd-workflow.md
---------
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
- Fix workflow_path in step-01-understand.md, step-02-investigate.md, and step-03-generate.md
- Changed from non-existent 'create-tech-spec' to correct 'quick-spec'
- Aligns with step-04-review.md which already had correct path
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* docs: radical reduction of documentation scope for v6 beta
Archive and basement unreviewed content to ship a focused, minimal doc set.
Changes:
- Archive stale how-to workflow guides (will rewrite for v6)
- Archive outdated explanation and reference content
- Move unreviewed content to basement for later review
- Reorganize TEA docs into dedicated /tea/ section
- Add workflow-map visual reference page
- Simplify getting-started tutorial and sidebar navigation
- Add explanation pages: brainstorming, adversarial-review, party-mode,
quick-flow, advanced-elicitation
- Fix base URL handling for subdirectory deployments (GitHub Pages forks)
The goal is a minimal, accurate doc set for beta rather than
comprehensive but potentially misleading content.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: restructure BMM and agents documentation by consolidating and flattening index files.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Directory was renamed in 1da77058 but step file contents weren't updated.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
Group "go-on" options first (Done, Begin Dev), then reasoning options
(Advanced Elicitation, Party Mode, Adversarial Review).
Follows established pattern: most common action first, related options grouped.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix(quick-spec): change menu shortcuts to avoid Approve/Advanced confusion
Users were typing 'a' expecting to Approve (since it starts with A) but
triggering Advanced Elicitation instead. Changed shortcuts to:
- [C] Continue (was [Y] Approve)
- [E] Edit (was [C] Changes)
This keeps [A] for Advanced Elicitation consistent with other workflows.
Fixes user-reported UX issue with confusing menu shortcuts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(quick-dev): standardize menu shortcuts to use intuitive letters
- Change [T] to [P] for "Plan first" (P matches the label)
- Change [1][2][3] to [W][F][S] for findings resolution:
- [W] Walk through
- [F] Fix automatically
- [S] Skip
Consistent with letter-based menu pattern used elsewhere.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Update quick-spec and quick-dev workflow menus to match established standards:
- Uppercase all menu option letters ([A], [P], [C], [T], [E], [W], etc.)
- Add "Menu Handling Logic:" sections with IF/THEN structure
- Add "EXECUTION RULES:" sections with halt/wait behavior
- Add chat handling for checkpoint menus (A/P/C)
- Remove code blocks from Display patterns, use standard format
- Add header for adversarial review process block
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
When provided, the style_guide input overrides all generic principles
(including Microsoft Style Guide baseline, reader-type priorities, and
structure-model selection) except CONTENT IS SACROSANCT.
Changes to both editorial-review-structure.xml and editorial-review-prose.xml:
- Add style_guide input after content input
- Add STYLE GUIDE OVERRIDE instruction in llm section
- Add "Consult style_guide" action in Step 3 for mid-flow refresh
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
Replace ambiguous "execute" terminology with explicit "Read fully and follow:"
phrasing across all workflow files to prevent LLM goal-seeking behavior where
models attempt to "achieve the end result" rather than following step-by-step
instructions verbatim.
Changes:
- Update 5 handler templates with canonical phrasing
- Replace ~150 INSTRUCTIONAL patterns across 87 workflow files
- Add "[Workflow] complete." prefix to 7 workflow endpoints
- Preserve BEHAVIORAL/STRUCTURAL patterns (agent descriptions, XML tags)
- Fix gitignore and markdownlint to ignore all node_modules directories
Closes#1372
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add an optional also_consider parameter that allows callers to pass
domain-specific areas to keep in mind during review. This gently nudges
the reviewer toward specific concerns without overriding normal analysis.
Testing showed:
- Specific items steer strongly (questions get directly answered)
- Domain-focused items shift the lens (e.g., security focus = deeper security findings)
- Vague items have minimal effect (similar to baseline)
- Single items nudge without dominating
- Contradictory items handled gracefully
Includes test cases with sample content and 10 configurations to validate
the parameter behavior across different use cases.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
The correct-course workflow restructures epics but did not update
sprint-status.yaml, leaving tracking out of sync. Added check-item 6.4
to Section 6 (after user approval) to update sprint-status.yaml when
epics are added, removed, renumbered, or stories are modified.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add editorial review tasks for structure and prose
Add two complementary editorial review tasks:
- editorial-review-structure.xml: Structural editor that proposes cuts,
reorganization, and simplification. Includes 5 document archetype models
(Tutorial, Reference, Explanation, Prompt, Strategic) for targeted evaluation.
- editorial-review-prose.xml: Clinical copy-editor for prose improvements
using Microsoft Writing Style Guide as baseline.
Both tasks support humans and llm target audiences with different principles.
* fix: add content-sacrosanct guardrail to editorial review tasks
Both editorial review tasks (prose and structure) were missing the key
constraint that reviewers should never challenge the ideas/knowledge
themselves—only how clearly they are communicated. This restores the
original design intent.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: align reader_type parameter naming across editorial tasks
Prose task was using 'target_audience' for the humans/llm optimization
flag while structure task correctly separates 'target_audience' (who
reads) from 'reader_type' (optimization mode). Aligns to reader_type.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
Step 4 was missing a structured menu at the spec review checkpoint.
This caused agents to skip past the approval step without waiting for
explicit user confirmation.
Added:
- Review menu with [y] Approve, [c] Changes, [q] Questions, [a] Advanced Elicitation, [p] Party Mode
- Explicit HALT instruction
- Menu handling section
This aligns step 4 with the menu-driven pattern used in steps 1-3.
Fixes#1304
Also fixes pre-existing prettier issue in src/modules/cis/module.yaml.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Jonah Schulte
Alex Verkhovsky
Michael Pursifull
Brian Madison
Murat K Ozcan
Vladimir Hrusovsky
Eduard Voiculescu
sjennings
Brian