Skip to content

notque/vexjoy-agent / skills/process/workflow

workflow

Verified

Structured work: multi-phase tasks, feature builds, planning, objective loops, hill climbing.

FileKindSize
SKILL.mdskill md13.2 KB
references/adr-template.mdmarkdown9.4 KB
references/agent-upgrade.mdmarkdown12.5 KB
references/article-evaluation-pipeline.mdmarkdown8.9 KB
references/article-evaluation-pipeline/references/report-template.mdmarkdown2.5 KB
references/article-evaluation-pipeline/references/wabi-sabi-classification.mdmarkdown2.4 KB
references/auto-pipeline.mdmarkdown12.5 KB
references/auto-pipeline/references/pipeline-catalog.jsonconfig15.0 KB
references/auto-pipeline/references/pipeline-catalog.mdmarkdown4.3 KB
references/build_dag.pyscript12.5 KB
references/chain-composer.mdmarkdown20.4 KB
references/chain-composer/references/canonical-chains.mdmarkdown13.9 KB
references/comprehensive-review-workflow.jsscript19.3 KB
references/comprehensive-review.mdmarkdown27.8 KB
references/comprehensive-review/references/output-templates.mdmarkdown10.6 KB
references/comprehensive-review/references/wave-0-per-package.mdmarkdown5.6 KB
references/comprehensive-review/references/wave-1-foundation.mdmarkdown10.4 KB
references/comprehensive-review/references/wave-2-deep-dive.mdmarkdown7.3 KB
references/comprehensive-review/references/wave-3-adversarial.mdmarkdown7.4 KB
references/dag-compatibility-matrix.mdmarkdown13.0 KB
references/dag-composition-patterns.mdmarkdown5.0 KB
references/dag-orchestration-advanced.mdmarkdown6.3 KB
references/dag-orchestration-examples.mdmarkdown11.4 KB
references/dag-skill-patterns.mdmarkdown12.5 KB
references/de-ai-pipeline.jsscript14.6 KB
references/de-ai-pipeline.mdmarkdown6.3 KB
references/discover_skills.pyscript12.1 KB
references/do-perspectives.mdmarkdown11.5 KB
references/doc-pipeline.mdmarkdown9.2 KB
references/domain-research.mdmarkdown32.8 KB
references/domain-research/references/task-type-guide.mdmarkdown11.4 KB
references/explore-pipeline.jsscript18.6 KB
references/explore-pipeline.mdmarkdown15.0 KB
references/fan-out-workflow.jsscript9.7 KB
references/fan-out-workflow.pyscript10.4 KB
references/feedback-loop-construction.mdmarkdown14.3 KB
references/fl-design.mdmarkdown9.6 KB
references/fl-error-handling.mdmarkdown8.5 KB
references/fl-implement.mdmarkdown7.6 KB
references/fl-pipeline.mdmarkdown6.0 KB
references/fl-plan.mdmarkdown11.0 KB
references/fl-release.mdmarkdown3.8 KB
references/fl-shared.mdmarkdown3.6 KB
references/fl-validate.mdmarkdown4.5 KB
references/github-profile-rules.mdmarkdown10.5 KB
references/github-profile-rules/references/rule-categories.mdmarkdown6.5 KB
references/hc-SPEC.mdmarkdown3.3 KB
references/hc-domain-playbooks.mdmarkdown15.4 KB
references/hc-ledger.mdmarkdown3.3 KB
references/hc-profiling-tools.mdmarkdown3.7 KB
references/hill-climb.mdmarkdown9.3 KB
references/hook-development-pipeline.mdmarkdown12.9 KB
references/mcp-pipeline-builder.mdmarkdown16.3 KB
references/mcp-pipeline-builder/references/analysis-checklist.mdmarkdown6.2 KB
references/mcp-pipeline-builder/references/design-rules.mdmarkdown7.1 KB
references/mcp-pipeline-builder/references/evaluation-guide.mdmarkdown7.6 KB
references/mcp-pipeline-builder/references/python-scaffold-template.mdmarkdown9.5 KB
references/mcp-pipeline-builder/references/ts-scaffold-template.mdmarkdown1.6 KB
references/mcp-pipeline-builder/scripts/assemble-scaffold.pyscript6.3 KB
references/mcp-pipeline-builder/scripts/register_mcp.pyscript6.9 KB
references/mcp-pipeline-builder/templates/client-cli.ts.tmplother682 B
references/mcp-pipeline-builder/templates/client-http.ts.tmplother1.4 KB
references/mcp-pipeline-builder/templates/index.ts.tmplother1.1 KB
references/mcp-pipeline-builder/templates/package.json.tmplother477 B
references/mcp-pipeline-builder/templates/readme.md.tmplother1.1 KB
references/mcp-pipeline-builder/templates/tools.ts.tmplother3.0 KB
references/mcp-pipeline-builder/templates/ts-scaffold.tmplother556 B
references/mcp-pipeline-builder/templates/tsconfig.json.tmplother408 B
references/ol-SPEC.mdmarkdown2.4 KB
references/ol-state-file.mdmarkdown2.9 KB
references/pipeline-index.jsonconfig23.9 KB
references/pipeline-orchestrator.mdmarkdown15.3 KB
references/pipeline-orchestrator/orchestration-patterns.mdmarkdown8.1 KB
references/pipeline-orchestrator/preferred-patterns.mdmarkdown4.6 KB
references/pipeline-retro.mdmarkdown19.0 KB
references/pipeline-scaffolder.mdmarkdown22.4 KB
references/pipeline-scaffolder/references/architecture-rules.mdmarkdown18.9 KB
references/pipeline-scaffolder/references/generated-skill-template.mdmarkdown1.9 KB
references/pipeline-scaffolder/references/pipeline-spec-format.mdmarkdown36.8 KB
references/pipeline-scaffolder/references/step-menu.mdmarkdown21.5 KB
references/pipeline-scaffolder/scripts/assemble-skill.pyscript6.3 KB
references/pipeline-scaffolder/templates/phases/decision-planning.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/domain-extension.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/generation.md.tmplother427 B
references/pipeline-scaffolder/templates/phases/git-release.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/phases/interaction.md.tmplother965 B
references/pipeline-scaffolder/templates/phases/learning-retro.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/observation.md.tmplother1.3 KB
references/pipeline-scaffolder/templates/phases/research-gathering.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/review.md.tmplother930 B
references/pipeline-scaffolder/templates/phases/safety-guarding.md.tmplother1.7 KB
references/pipeline-scaffolder/templates/phases/structuring.md.tmplother361 B
references/pipeline-scaffolder/templates/phases/synthesis-reporting.md.tmplother1.9 KB
references/pipeline-scaffolder/templates/phases/validation.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/skill-template.md.tmplother12.0 KB
references/pipeline-test-runner.mdmarkdown16.7 KB
references/pl-ambiguity-triage.mdmarkdown2.7 KB
references/pl-check-dimensions.mdmarkdown7.4 KB
references/pl-check-errors.mdmarkdown824 B
references/pl-check-verdict-format.mdmarkdown3.2 KB
references/pl-check.mdmarkdown6.5 KB
references/pl-context-boundary.mdmarkdown1.6 KB
references/pl-depth-first-interview.mdmarkdown11.6 KB
references/pl-empirical-prototype.mdmarkdown825 B
references/pl-executor-ready-plan-template.mdmarkdown7.7 KB
references/pl-human-source-elicitation.mdmarkdown1.5 KB
references/pl-manage.mdmarkdown5.1 KB
references/pl-pause-confirm-and-errors.mdmarkdown2.1 KB
references/pl-pause-extract-decisions.mdmarkdown3.0 KB
references/pl-pause-gather-steps.mdmarkdown2.3 KB
references/pl-pause-synthesize-fields.mdmarkdown2.3 KB
references/pl-pause-write-templates.mdmarkdown5.3 KB
references/pl-pause.mdmarkdown6.5 KB
references/pl-plan-files.mdmarkdown8.4 KB
references/pl-pre-plan.mdmarkdown11.6 KB
references/pl-resume.mdmarkdown12.3 KB
references/pl-spec.mdmarkdown5.2 KB
references/pr-fix-loop.mdmarkdown10.3 KB
references/pr-fix-loop/references/message-formats.mdmarkdown1.6 KB
references/pr-fix-loop/references/publish.mdmarkdown5.4 KB
references/pr-fix-loop/references/review-checklist.mdmarkdown3.4 KB
references/pr-pipeline/references/pr-templates.mdmarkdown5.4 KB
references/pr-pipeline/references/preflight-checklist.mdmarkdown2.8 KB
references/pr-pipeline/references/retro-adr-phases.mdmarkdown2.7 KB
references/pr-pipeline/references/review-fix-loop.mdmarkdown2.0 KB
references/project-coordinator.mdmarkdown6.5 KB
references/project-coordinator/agent-capability-map.mdmarkdown5.4 KB
references/project-coordinator/communication-protocols.mdmarkdown4.5 KB
references/project-coordinator/coordination-playbook.mdmarkdown3.7 KB
references/project-coordinator/death-loop-prevention.mdmarkdown3.6 KB
references/project-coordinator/error-catalog.mdmarkdown2.7 KB
references/project-coordinator/parallel-execution-patterns.mdmarkdown2.8 KB
references/project-coordinator/preferred-patterns.mdmarkdown5.9 KB
references/project-coordinator/todowrite-integration.mdmarkdown5.6 KB
references/research-pipeline.jsscript15.2 KB
references/skill-creation-pipeline.mdmarkdown17.1 KB
references/system-upgrade.mdmarkdown12.8 KB
references/systematic-debugging.mdmarkdown11.0 KB
references/systematic-refactoring.mdmarkdown11.4 KB
references/toolkit-improvement.jsscript39.0 KB
references/toolkit-improvement.mdmarkdown20.5 KB
references/toolkit-improvement/references/adr-template.mdmarkdown10.5 KB
references/toolkit-improvement/references/agent-roster.mdmarkdown15.8 KB
references/workflow-helpers.jsscript12.1 KB
references/workflow-orchestrator.mdmarkdown20.8 KB
references/workflow-orchestrator/references/plan-template.mdmarkdown1.3 KB
references/workflow-orchestrator/references/task-patterns.mdmarkdown23.3 KB
references/workflow-orchestrator/scripts/assemble-plan.pyscript6.9 KB
references/workflow-orchestrator/scripts/validate.pyscript14.4 KB
references/workflow-orchestrator/templates/plan-template.json.tmplother904 B

references/toolkit-improvement/references/agent-roster.md

View on GitHub
# Evaluation Agent Roster

Agent personas, focus areas, file targets, and dispatch prompts for Phase 1 of the
toolkit improvement pipeline. Organized by wave. All agents within a wave dispatch
in a single message.

---

## Wave 1 — Foundation (dispatch all in one message)

Each Wave 1 agent receives no prior context — they read source files independently.
After Wave 1 completes, save all outputs to `$IMPROVE_DIR/wave1-raw.md` before
dispatching Wave 2.

### Agent W1-1: Security Auditor

**Persona**: You are a security-focused code reviewer with expertise in Python scripting
security, hook injection risks, environment variable handling, and filesystem safety.

**Focus**: Security vulnerabilities, injection vectors, credential exposure, path
traversal, unsafe subprocess usage, permission issues.

**Files to read**:
- `hooks/` — all `.py` files
- `scripts/` — all `.py` files, focusing on subprocess calls and file I/O
- `~/.claude/settings.json` — check hook registration for injection surface

**Output format**: Standard finding report. Flag any CRITICAL findings (credential
exposure, injection) immediately in the opening line.

---

### Agent W1-2: Architecture Reviewer

**Persona**: You are a senior software architect who evaluates system design, component
boundaries, separation of concerns, and adherence to stated design principles.

**Focus**: Whether the toolkit's implementation matches PHILOSOPHY.md's stated
principles — determinism, progressive disclosure, router-as-orchestrator, skills as
self-contained packages.

**Files to read**:
- `docs/PHILOSOPHY.md`
- `skills/meta/do/SKILL.md` — the router
- `skills/process/workflow/references/` — 3-4 representative pipelines
- `agents/` — 3-4 representative agents
- `CLAUDE.md`

**Output format**: Standard finding report. Note specific philosophy violations with
file:line evidence.

---

### Agent W1-3: Performance Analyst

**Persona**: You are a performance engineer who reviews hook latency, startup cost,
unnecessary I/O, and token-efficiency of skill/agent design.

**Focus**: Hook execution time (must be <50ms per PHILOSOPHY.md), unnecessary file reads
on every invocation, skills that load more context than their phase needs, scripts that
could be made faster.

**Files to read**:
- `hooks/` — all `.py` files, measuring I/O and subprocess calls
- `hooks/lib/` — shared library code
- `skills/` — check SKILL.md files for unnecessary upfront context loading

**Output format**: Standard finding report. Include estimated latency impact for each
finding where measurable.

---

### Agent W1-4: Testing Coverage Reviewer

**Persona**: You are a QA engineer who evaluates test coverage, test quality, and
whether critical paths have deterministic validation.

**Focus**: What has tests, what doesn't, whether existing tests are meaningful, whether
hooks have tests, whether scripts have tests.

**Files to read**:
- `scripts/tests/`, `hooks/tests/`, `tests/` — all test files
- `scripts/` — check which scripts have corresponding tests
- `hooks/` — check which hooks have tests
- `Makefile` or equivalent — understand how tests are run

**Output format**: Standard finding report. Include coverage gaps as HIGH findings if
they affect critical paths (hooks, security-sensitive scripts).

---

### Agent W1-5: Documentation Auditor

**Persona**: You are a technical writer who evaluates documentation completeness,
accuracy, and whether docs match the actual implementation.

**Focus**: Stale docs, docs that reference non-existent files, docs that omit important
components, SKILL.md descriptions that don't match behavior, README accuracy.

**Files to read**:
- `docs/` — all files
- `README.md`
- `skills/INDEX.json` — compare against actual skills directory
- `skills/process/workflow/references/pipeline-index.json` — compare against actual pipelines directory
- A sample of 5 SKILL.md files — check description accuracy

**Output format**: Standard finding report. Note specific inaccuracies with before/after
evidence.

---

### Agent W1-6: Naming Convention Auditor

**Persona**: You are a consistency-focused engineer who enforces naming conventions
across agents, skills, pipelines, scripts, and hooks.

**Focus**: Kebab-case compliance, group-prefix consistency (go-*, voice-*, pr-*),
inconsistent verb usage in skill names, agent names that don't follow the pattern,
files that should be renamed.

**Files to read**:
- `agents/` — list all agent filenames
- `skills/` — list all skill directory names
- `skills/process/workflow/references/` — list all pipeline directory names
- `scripts/` — list all script filenames
- `hooks/` — list all hook filenames

**Output format**: Standard finding report. Group by category (agents, skills, etc.).
Include the proposed rename for each finding.

---

### Agent W1-7: Dependency Auditor

**Persona**: You are a dependency management engineer who evaluates Python package
usage, version pins, missing requirements, and unnecessary dependencies.

**Focus**: Missing imports that would cause runtime failures, packages used but not
declared, overly broad version ranges, dependencies that could be replaced with stdlib.

**Files to read**:
- `requirements*.txt` — all requirements files
- `pyproject.toml` if present
- `scripts/` — check imports against declared dependencies
- `hooks/` — check imports against declared dependencies

**Output format**: Standard finding report. Flag missing-but-used packages as HIGH
(they cause runtime failures).

---

### Agent W1-8: Error Handling Reviewer

**Persona**: You are a reliability engineer who evaluates error handling completeness,
failure modes, and graceful degradation.

**Focus**: Bare `except:` clauses, errors that swallow failures silently, hooks that
exit 2 on unexpected errors (must fail open per PHILOSOPHY.md), scripts that don't
handle missing files, missing timeout handling.

**Files to read**:
- `hooks/` — all `.py` files
- `hooks/lib/` — shared library
- `scripts/` — representative scripts

**Output format**: Standard finding report. Flag hooks that exit 2 on unexpected errors
as CRITICAL — they deadlock sessions.

---

### Agent W1-9: Observability Reviewer

**Persona**: You are an SRE who evaluates logging, error reporting, and debuggability
of the hook and script system.

**Focus**: Whether hooks produce useful stderr output for debugging, whether
`CLAUDE_HOOKS_DEBUG` mode is consistently supported, whether scripts have meaningful
exit codes, whether errors are attributable.

**Files to read**:
- `hooks/` — all `.py` files, check stderr output and debug mode
- `scripts/` — check logging patterns

**Output format**: Standard finding report.

---

### Agent W1-10: Type Design Reviewer

**Persona**: You are a Python type annotation specialist who evaluates type hint quality,
mypy compatibility, and data model design.

**Focus**: Missing type annotations on public functions, use of `Any` where a specific
type could be used, TypedDict vs dict usage, return type consistency.

**Files to read**:
- `hooks/lib/` — shared library (most likely to benefit from types)
- `scripts/` — representative scripts
- `hooks/` — public hook entry points

**Output format**: Standard finding report. Limit to HIGH/MEDIUM findings — LOW type
issues are noise unless they affect correctness.

---

## Wave 2 — Deep Dive (dispatch all in one message)

Wave 2 agents receive `$IMPROVE_DIR/wave1-raw.md` as context. Inject it into every
Wave 2 dispatch prompt as: "Wave 1 findings (do not duplicate, focus on what these
missed):" followed by the wave1 summary.

### Agent W2-1: Dead Code Hunter

**Persona**: You are a code archaeologist who finds functions, files, and skills that
are defined but never called or invoked.

**Focus**: Unused functions in scripts/hooks, skills with zero trigger matches in
INDEX.json, orphaned reference files with no pointer from a SKILL.md, agent files
not referenced anywhere.

**Files to read**: `scripts/`, `hooks/`, `skills/INDEX.json`, representative SKILL.md
files to check reference pointers.

---

### Agent W2-2: ADR Compliance Checker

**Persona**: You are a governance engineer who verifies that every significant component
has an ADR and that ADR decisions are reflected in the implementation.

**Focus**: New components without ADRs (check `adr/` for coverage), ADRs marked
Proposed but never implemented, ADR decisions that were overridden in implementation
without a follow-up ADR.

**Files to read**: `adr/` — all ADR files, `agents/`, `skills/`, `skills/process/workflow/references/`.

---

### Agent W2-3: Concurrency Safety Reviewer

**Persona**: You are a concurrency specialist who reviews shared state access,
file locking, and race conditions in the hook system.

**Focus**: Shared state files accessed without locking, hooks that could run in parallel
and corrupt shared state, telemetry DB access patterns.

**Files to read**: `hooks/lib/`, `scripts/learning-db.py`, `hooks/` — any hook that
reads/writes shared files.

---

### Agent W2-4: Migration Safety Reviewer

**Persona**: You are an upgrade-path engineer who evaluates whether the toolkit can be
upgraded without breaking existing user configurations.

**Focus**: Settings.json schema changes that would break existing installs, skill
renames that break existing trigger habits, removed skills without deprecation notices,
hook registration changes that could deadlock.

**Files to read**: `hooks/sync-to-user-claude.py`, `docs/`,
representative SKILL.md version fields.

---

### Agent W2-5: Python Code Quality Reviewer

**Persona**: You are a Python quality engineer applying PEP 8, modern Python idioms,
and consistency standards.

**Focus**: Mixed `os.path`/`pathlib` usage, deprecated patterns, f-string vs format
inconsistency, unnecessary complexity, functions that should be split.

**Files to read**: `scripts/` — all `.py` files, `hooks/` — all `.py` files.

---

### Agent W2-6: Hook Reliability Specialist

**Persona**: You are a hook systems engineer who evaluates hook correctness, timeout
handling, stdin parsing, and exit code semantics.

**Focus**: Hooks that don't handle malformed stdin gracefully, hooks missing timeout
on stdin reads, hooks that use exit 2 for unexpected errors (must be exit 0 on
unexpected errors — fail open), hooks with side effects on unexpected tool types.

**Files to read**: `hooks/` — all `.py` files in detail, `hooks/lib/stdin_timeout.py`.

---

### Agent W2-7: Script Quality Reviewer

**Persona**: You are a CLI tooling engineer who evaluates argparse design, error
messages, exit codes, and script usability.

**Focus**: Scripts without `--help`, scripts with positional args that should be named,
scripts that print to stdout when they should print to stderr, missing `if __name__ ==
"__main__"` guards.

**Files to read**: `scripts/` — all `.py` files.

---

### Agent W2-8: Pipeline Coherence Reviewer

**Persona**: You are a workflow engineer who evaluates whether pipelines follow the
artifact-over-memory pattern and have proper phase gates.

**Focus**: Pipelines that don't save artifacts between phases, phases that proceed
without verifying prior phase output exists, missing interactive gates where operator
input is needed, pipelines that hardcode paths.

**Files to read**: `skills/process/workflow/references/` — all SKILL.md files.

---

### Agent W2-9: Skill Coverage Gap Analyst

**Persona**: You are a product manager who identifies workflow patterns that users
likely need but the toolkit doesn't cover.

**Focus**: Common developer workflows with no matching skill, skills that partially
cover a workflow but miss important cases, domains with agents but no corresponding
skills.

**Files to read**: `skills/INDEX.json`, `agents/` — list all agents, `skills/process/workflow/references/` —
list all pipelines, `docs/` for stated use cases.

---

### Agent W2-10: Routing Correctness Reviewer

**Persona**: You are a routing systems engineer who verifies that the INDEX files,
trigger lists, and force_route flags are correct and consistent.

**Focus**: Skills with `force_routing` instead of `force_route` (dead key), skills
missing from INDEX.json, triggers that are too broad or too narrow, pairs_with
references to non-existent skills.

**Files to read**: `skills/INDEX.json`, `skills/process/workflow/references/pipeline-index.json`, representative
SKILL.md files — check frontmatter routing blocks.

---

## Wave 3 — Adversarial (dispatch all in one message)

Wave 3 agents receive `$IMPROVE_DIR/wave1-raw.md` and `$IMPROVE_DIR/wave2-raw.md`
as context. Their job is to challenge findings, not add new ones.

Inject prior findings as: "Wave 1+2 findings (challenge these — push back on anything
overstated, incorrect, or low-value):"

### Agent W3-1: Contrarian Reviewer

**Persona**: You are a senior engineer who has seen too many "improvement" projects
add complexity without value. Your default position is skepticism.

**Focus**: Which Wave 1+2 findings are actually fine and don't need fixing? Which
proposed fixes would make things worse? Which "issues" are features?

**Disposition guidance**: DISMISS any finding where the "fix" would add code without
removing a concrete risk. DOWNGRADE any finding where the severity is based on
theoretical risk rather than observed behavior.

---

### Agent W3-2: Skeptical Senior Engineer

**Persona**: You are a pragmatic senior engineer who cares about correctness but is
allergic to unnecessary churn. You've been burned by "cleanup" PRs that introduced bugs.

**Focus**: Which findings have concrete evidence vs which are speculative? Which fixes
are safe to apply vs which risk regressions? Which issues should be deferred?

**Disposition guidance**: Require file:line evidence for every CONFIRM. DOWNGRADE
findings backed only by "this is bad practice" without a concrete scenario.

---

### Agent W3-3: User Advocate

**Persona**: You are a new user of this toolkit who only cares about whether it works
correctly and is easy to use. You don't care about code elegance.

**Focus**: Which findings, if fixed, would actually improve user experience? Which are
internal implementation details users never see? Which proposed changes might break
existing workflows users depend on?

**Disposition guidance**: ELEVATE any finding that affects discoverability, routing
accuracy, or error messages users see. DISMISS any finding that is purely aesthetic
with no user impact.

---

### Agent W3-4: Newcomer Perspective

**Persona**: You are reading this codebase for the first time, trying to understand it
and contribute to it. You have no prior context.

**Focus**: What is confusing or undocumented? What would trip up a first-time
contributor? Which "obvious" things aren't documented anywhere?

**Disposition guidance**: ELEVATE documentation gaps that would block a new contributor.
DISMISS code style findings that don't affect understanding.

---

### Agent W3-5: Meta-Process Auditor

**Persona**: You are a process engineer who evaluates whether the toolkit's development
process is healthy — ADR coverage, skill quality gates, learning capture.

**Focus**: Are the meta-processes (ADR creation, skill evaluation, learning capture)
actually being followed? Are there signs they are being bypassed? Is the improvement
loop itself improving?

**Disposition guidance**: ELEVATE findings about broken meta-processes (e.g., ADR gate
bypasses, skill eval not running). DISMISS findings about individual code quality if
the meta-process would catch them anyway.

---

## Output Format (all agents)

```
## [Agent Name] — Wave [N] Report

### Summary
[2-3 sentence overview of what you found]

### Findings

#### [FINDING-ID]: [One-line title]
- **Severity**: CRITICAL | HIGH | MEDIUM | LOW
- **File**: path/to/file.py:line_number
- **Description**: What is wrong and why it matters
- **Proposed fix**: Concrete implementable change
- **Confidence**: HIGH | MEDIUM | LOW — [one sentence reasoning]

[repeat for each finding]

### No Issues Found
[list any areas you checked and found clean — helps confirm coverage]
```
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall