Skip to content

backlog: close the survivors — two more skills, references/ rename #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
krwhynot merged 2 commits into from
Sep 2, 2026
Merged

backlog: close the survivors — two more skills, references/ rename #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3923da7
backlog: close the survivors — troubleshoot and codex-challenge becom…
krwhynot Sep 2, 2026
902594d
merge main
krwhynot Sep 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,3 @@ desktop.ini
# Local overrides
*.local.md
*.local.json

# VS Code (keep settings.json and extensions.json, ignore personal)
.vscode/launch.json
.vscode/*.code-workspace
12 changes: 12 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,18 @@
single long command loses its later phases after context compaction in
exactly the long sessions a nine-phase workflow produces. Tests that read
Phase 5 content now point at `phases/phase-5-audit.md`.
- **`/deepgrade:troubleshoot` and `/deepgrade:codex-challenge` are skills**, on
the same router-plus-phase-files layout as `plan`. troubleshoot (854 lines)
becomes a 256-line router with the incident pre-flow, four phases,
multi-agent mode, and knowledge-base write-back in one file each;
codex-challenge (533 lines) becomes a 213-line router with the output
schema, prompt template, round loop, and report split out. The parser
tests now bind to `skills/codex-challenge/phases/output-schema.md`. The
three remaining long commands (quick-cleanup, readiness-generate,
plan-export) are under the documented 500-line guidance and stay as
commands. Closes backlog B07.
- The documentation skill's bundled templates live in `references/`, the
documented convention, instead of `resources/`. Closes backlog B28.
- The `(deepgrade)` description prefix is stripped from all 23 commands and
skills. After the monorepo split it mislabelled 11 files owned by
deepgrade-audit and deepgrade-readiness.
Expand Down
10 changes: 5 additions & 5 deletions interop.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,12 +24,12 @@ Format rules (the sweep depends on them):
| Artifact | Producer | Consumers |
| -------- | -------- | --------- |
| docs/audit/readability/readability-score.json | plugins/deepgrade-readiness/commands/readiness-scan.md | plugins/deepgrade-audit/agents/gate-generator.md, plugins/deepgrade-audit/agents/delta-scanner.md, plugins/deepgrade-audit/commands/codebase-delta.md |
| docs/audit/readability/readability-report.md | plugins/deepgrade-readiness/agents/readiness-report-generator.md | plugins/deepgrade-audit/commands/codebase-audit.md, plugins/deepgrade-audit/agents/delta-scanner.md, plugins/deepgrade/skills/documentation/resources/spec-template.md |
| docs/audit/readability/readability-report.md | plugins/deepgrade-readiness/agents/readiness-report-generator.md | plugins/deepgrade-audit/commands/codebase-audit.md, plugins/deepgrade-audit/agents/delta-scanner.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
| docs/audit/deepgrade-report.md | plugins/deepgrade-audit/agents/deepgrade-report-generator.md | plugins/deepgrade/scripts/dg-session-start.js |
| docs/audit/risk-assessment.md | plugins/deepgrade-audit/agents/risk-assessor.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/resources/spec-template.md |
| docs/audit/dependency-map.md | plugins/deepgrade-audit/agents/dependency-mapper.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/resources/spec-template.md |
| docs/audit/feature-inventory.md | plugins/deepgrade-audit/agents/feature-scanner.md | plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/resources/spec-template.md |
| docs/audit/integration-scan.md | plugins/deepgrade-audit/agents/integration-scanner.md | plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/resources/spec-template.md |
| docs/audit/risk-assessment.md | plugins/deepgrade-audit/agents/risk-assessor.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
| docs/audit/dependency-map.md | plugins/deepgrade-audit/agents/dependency-mapper.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
| docs/audit/feature-inventory.md | plugins/deepgrade-audit/agents/feature-scanner.md | plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
| docs/audit/integration-scan.md | plugins/deepgrade-audit/agents/integration-scanner.md | plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
| docs/audit/audit-progress.md | plugins/deepgrade-audit/commands/codebase-audit.md | plugins/deepgrade-readiness/agents/baseline-scanner.md |

## The readability-score.json schema
Expand Down
8 changes: 6 additions & 2 deletions plugins/deepgrade/GUIDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

# DeepGrade Knowledge Guide v7.1.0

**8 Commands**  •  **2 Agents**  •  **4 Skills**  •  **3 Safety Hooks**  •  **Requires Node.js 18+**
**6 Commands**  •  **2 Agents**  •  **6 Skills**  •  **3 Safety Hooks**  •  **Requires Node.js 18+**

[![Plugin](https://img.shields.io/badge/Claude_Code-Plugin-5A45FF?style=for-the-badge)](https://github.com/krwhynot/deepgrade)
[![Version](https://img.shields.io/badge/v7.1.0-stable-2ECC71?style=for-the-badge)](#)
Expand Down Expand Up @@ -161,12 +161,16 @@ methodology reference lives in the monorepo's
| ![p](https://img.shields.io/badge/-%E2%80%8B-9B59B6) | plan-scaffolder | Creates structured technical plans from vague objectives using 3 parallel analysts | quick-plan, plan |
| ![p](https://img.shields.io/badge/-%E2%80%8B-9B59B6) | plan-auditor | Scores plans across 8 dimensions using parallel specialist subagents | quick-audit, plan |

## The 4 Skills
## The 6 Skills

Skills are persistent knowledge that loads automatically when relevant — reference books the plugin carries in its back pocket.

**plan** -- The `/deepgrade:plan` workflow itself. `SKILL.md` is a router (identity, lifecycle, workspace layout, Step 0 intent detection) and each of the nine phases lives in its own file under `phases/`, read when the phase is entered. Split this way so the later phases survive context compaction in long planning sessions instead of being silently dropped with the rest of a 1,700-line command.

**troubleshoot** -- The `/deepgrade:troubleshoot` workflow: a router holding identity, timeline logging, plan detection, and Step 0 knowledge-base lookup, with the incident pre-flow, the four phases, multi-agent mode, and the knowledge-base write-back in one file each under `phases/`, read on entry.

**codex-challenge** -- The `/deepgrade:codex-challenge` loop: a router holding the Codex invocation pattern and the eight review dimensions, with the output schema, prompt template, round loop, and report in `phases/`. The schema file is what the parser tests bind to.

**documentation** -- The dispatch hub for document generation. Contains routing logic (first word = subcommand), 6 template references, smart suggestions when audit data exists, and document chain enforcement (a PRD triggers a check for a related BRD, etc.). Loads when you ask for a document, or invoke `/deepgrade:documentation` directly.


Expand Down
6 changes: 3 additions & 3 deletions plugins/deepgrade/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ Verify inside a Claude Code session:
/deepgrade:help
```

## Commands (8)
## Commands (6)

### Planning

Expand All @@ -51,7 +51,7 @@ Verify inside a Claude Code session:
| `/deepgrade:troubleshoot` | 4-phase debugging framework with incident triage and containment |
| `/deepgrade:help` | Show all commands and usage |

`/deepgrade:plan` and `/deepgrade:documentation` are skill surfaces; the other entries are command files.
`/deepgrade:plan`, `/deepgrade:troubleshoot`, `/deepgrade:codex-challenge`, and `/deepgrade:documentation` are skill surfaces; the other entries are command files.

## Safety Hooks (3)

Expand Down Expand Up @@ -92,7 +92,7 @@ present and wrong.
## Architecture

- **2 agents** - plan-auditor (the isolated judge) and plan-scaffolder
- **4 skills** - plan (router plus one file per phase), documentation, MCP research, self-audit knowledge
- **6 skills** - plan, troubleshoot, and codex-challenge (each a router plus one file per phase), documentation, MCP research, self-audit knowledge
- **6 doc templates** - ADR, BRD, PRD, README, release notes, spec
- **3 hook handlers** - `scripts/dg-*.js` plan-context layer, plus the
`dg-canary.js` / `dg-evidence-validate.js` audit tooling invoked by `/deepgrade:plan`
Expand Down
Loading
Loading