exograph-code-quality-review
Run a coverage-accountable, unusually strict review of Exograph for correctness, structural simplicity, deep modules, lifecycle safety, performance, tests…
Skill by k3nnethfrancis
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/k3nnethfrancis-exograph-code-quality-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/exograph-code-quality-review
What's inside
- Skill name
exograph-code-quality-review- Description
- Run a coverage-accountable, unusually strict review of Exograph for correctness, structural simplicity, deep modules, lifecycle safety, performance, tests, and repository health. Use for whole-repository audits, architecture cleanup, launch reviews, thermonuclear code-quality reviews, or any pass that must prove which files were inspected and what remains unseen.
- License
- Apache-2.0
- Instructions
- 131 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- rubric.md · references/
- review-map.mjs · scripts/
- review-map.test.mjs · scripts/
SKILL.md (first lines)
# Exograph Code Quality Review
Raise the approval bar above “works and passes tests.” Seek behavior-preserving
changes that delete concepts, branches, fallback paths, and unearned seams.
Prove coverage instead of implying it.
## Start the review
1. Read the root `AGENTS.md`, architecture, glossary, and the closest
subdirectory `AGENTS.md`.
2. Freeze the scope: repository root, commit, base ref if reviewing a diff, and
whether the pass is diagnostic or authorized to fix.
3. Read [references/rubric.md](references/rubric.md).
4. Initialize the private review map:
```sh
node skills/exograph-code-quality-review/scripts/review-map.mjs init
```
The default state is `docs/internal/code-quality-review/state.json`, which is
ignored. Never commit review ledgers, agent logs, or generated reports.
## Traverse methodically
Review logical clusters, not arbitrary directory slices.
1. Start at an entrypoint, public contract, changed file, or high-risk owner.
2. After inspecting a file, follow the relationship that can validate or
falsify your current model:
- import or exporter;
- importer or caller;
- owning test;
- linked contract or architecture document.
3. Ask for a bounded frontier:
```sh
node skills/exograph-code-quality-review/scripts/review-map.mjs frontier \
--from packages/core/src/workspace-graph.ts --depth 2 --page-size 12
```
Narrow a noisy hub without losing the recorded graph:
```sh
node skills/exograph-code-quality-review/scripts/review-map.mjs frontier \
--from packages/core/src/workspace-graph.ts \
--relation imports --relation tests --depth 2
```
4. State why the next file follows before reading it. Prefer the file that
tests an invariant or crosses a seam over the merely adjacent file.
5. Mark each file only after inspecting it:
```sh
node skills/exograph-code-quality-review/scripts/review-map.mjs mark \
--file packages/core/src/workspace-graph.ts \
--status reviewed \
--reason "Graph owner; traced construction, consumers, and focused tests" \
--evidence "pnpm --filter @exograph/core exec vitest run src/__tests__/workspace-graph.test.ts"
```
Use `excluded` only with a concrete reason such as generated binary, pinned
fixture, or vendored source. “Low risk” is not an exclusion reason. Re-running
`init` preserves a review only while the file content hash is unchanged.
## Review standard
Apply the rubric to the cluster, not just individual lines. In particular:
- search for a code-judo move that removes complexity instead of relocating it;
- evaluate module depth, interface burden, seam placement, and ownership;
- trace state, errors, concurrency, cancellation, persistence, and cleanup
through their complete lifecycle;
- distinguish deliberate compatibility from stale fallbacks;
- verify public and durable contracts at their owning interface;
- prefer a few high-conviction findings with mechanisms and evidence over a
long list of style nits.
Do not split a cohesive deep module merely because it is large. File size is a
reason to inspect interface burden and mixed ownership, not a verdict.
## Verify findings
For every finding:
1. Cite the smallest relevant file and line range.
2. Explain the mechanism and observable consequence.
3. Trace callers, consumers, tests, and cleanup paths until no accessible
evidence is left unchecked.
4. Reproduce or write the smallest discriminating test when feasible.
5. Propose the smallest structural remedy and name what it deletes.
6. Separate confirmed defects from design opportunities and unknowns.
Never report “this may be handled elsewhere” when the repository lets you
check. Never preserve a claim that focused evidence disproves.
## Close coverage
Run:
```sh
node skills/exograph-code-quality-review/scripts/review-map.mjs report
```
A whole-repository pass is complete only when:
- every in-scope tracked file is `reviewed` or explicitly `excluded`;
- no changed file has a stale review hash;
- every high-risk cycle or cross-owner seam has been inspected as a cluster;
- high-conviction findings have verification evidence;
- the report names remaining blocked work and unseen frontier truthfully; and
- focused gates pass before the broad repository gate.
Coverage is not approval. A reviewed repository can still fail the quality bar.
## Exograph-specific invariants
Defer to the owning `AGENTS.md` and stability Skills. At minimum preserve:
- explicit Note Root filesystem authority;From k3nnethfrancis/exograph, Apache-2.0.
More from k3nnethfrancis/exograph
- 0.584score
agent-first-software-engineering
k3nnethfrancis
Audit or improve Exograph so an external coding agent can understand, change, verify, and hand off work with minimal human relay.
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
ontology-design
k3nnethfrancis
Inspect an existing Markdown Workspace and propose the smallest evidence-backed ontology.yaml without changing the Workspace.
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
graph-system-stability
k3nnethfrancis
Use before changing Exograph graph domain types, snapshot construction, relationship extraction, graph queries, Note Root Formats, Workspace Ontology…
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
submit-exograph-issue
k3nnethfrancis
Use when a user reports an Exograph bug, QA finding, setup failure, confusing UX, regression, crash, terminal/rendering issue, graph/search/invocation/review…
SkillBFreshness: B★ 5Claude Code +9 - 0.576score
terminal-stability
k3nnethfrancis
Use before changing Exograph terminal runtime, rendering, settings, tests, or terminal-backed Command launch behavior.
SkillBFreshness: B★ 5Claude Code +9 - 0.576score
exograph-publishing
k3nnethfrancis
Support an Exograph user's website publishing, Quartz theme changes, deployment failures, and publishing-folder cleanup.
SkillBFreshness: B★ 5Claude Code +9 - 0.576score
exograph-cli
k3nnethfrancis
Use Exograph's local `exo` CLI to select a Markdown workspace, inspect retrieval health, search its exocortex, open notes, manage terminals, and invoke…
SkillBFreshness: B★ 5Claude Code +9 - 0.571score
find-and-connect-relevant-context
k3nnethfrancis
Find a small number of useful, evidence-backed connections for one selected note using Exograph's active graph and ontology.
SkillBFreshness: B★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 0
- Open issues
- 48
- Last commit (this folder)
- Jul 31, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/k3nnethfrancis/exograph
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from k3nnethfrancis
- 0.584score
agent-first-software-engineering
k3nnethfrancis
Audit or improve Exograph so an external coding agent can understand, change, verify, and hand off work with minimal human relay.
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
ontology-design
k3nnethfrancis
Inspect an existing Markdown Workspace and propose the smallest evidence-backed ontology.yaml without changing the Workspace.
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
graph-system-stability
k3nnethfrancis
Use before changing Exograph graph domain types, snapshot construction, relationship extraction, graph queries, Note Root Formats, Workspace Ontology…
SkillBFreshness: B★ 5Claude Code +9 - 0.579score
submit-exograph-issue
k3nnethfrancis
Use when a user reports an Exograph bug, QA finding, setup failure, confusing UX, regression, crash, terminal/rendering issue, graph/search/invocation/review…
SkillBFreshness: B★ 5Claude Code +9 - 0.576score
terminal-stability
k3nnethfrancis
Use before changing Exograph terminal runtime, rendering, settings, tests, or terminal-backed Command launch behavior.
SkillBFreshness: B★ 5Claude Code +9 - 0.576score
exograph-publishing
k3nnethfrancis
Support an Exograph user's website publishing, Quartz theme changes, deployment failures, and publishing-folder cleanup.
SkillBFreshness: B★ 5Claude Code +9
Cite this page
exograph-code-quality-review skill. Agent Mart. https://agentmart.dev/skills/k3nnethfrancis-exograph-code-quality-review (last updated 2026-10-24)