health

Name: health
Author: tomevault-io

Security Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Verify Codex configuration health — AGENTS.md, hooks, config.toml, agents, skills, secrets scan, and MCP reachability. Reports ✅…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Steps”, “1. AGENTS.md”, “2. config.toml”, “3. hooks.json”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name health directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Steps / 1. AGENTS.md / 2. config.toml” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Health Skill — Codex Configuration Validation

Verify that the Codex Brain configuration is healthy and complete.

Steps

1. AGENTS.md

Exists and is not empty
Line count: wc -l < AGENTS.md
Size: wc -c < AGENTS.md (budget: ≤32KB = 32768 bytes)
Contains key sections: Skills Roster, Exit Checklist, Terminal Rules

2. config.toml

.codex/config.toml exists and is valid TOML
Has #:schema directive on first line
Has codex_hooks = true under [features]

3. hooks.json

.codex/hooks.json exists and is valid JSON: jq . .codex/hooks.json
Hook count: jq '[.. | objects | select(has("command"))] | length' .codex/hooks.json

4. Hook Scripts

All .codex/hooks/*.sh files exist and are executable:

for h in .codex/hooks/*.sh; do test -x "$h" || echo "NOT_EXEC: $h"; done

5. Subagents

All .codex/agents/*.toml files exist

Each has name, description, developer_instructions fields:

for f in .codex/agents/*.toml; do grep -q 'developer_instructions' "$f" || echo "INCOMPLETE: $f"; done

6. Skills

All .agents/skills/*/SKILL.md files exist

Each has name: and description: in frontmatter:

for f in .agents/skills/*/SKILL.md; do grep -q '^name:' "$f" || echo "BAD FRONTMATTER: $f"; done

7. Error Log

brain/tasks/CODEX_ERRORS.md exists (warn if missing)

8. Secrets Scan

git ls-files | xargs grep -l 'BEGIN.*PRIVATE KEY\|password\s*=\s*[^{][^"\x27]\{8,\}' 2>/dev/null | head -10

Report any matches as ⚠️ warnings.

9. MCP Tool Reachability

Check that the required runtimes are available (all MCP tools run via uvx or npx):

command -v uvx &>/dev/null && echo "uvx: ✅" || echo "uvx: ❌ missing — install via: pip install uv"
command -v npx &>/dev/null && echo "npx: ✅" || echo "npx: ⚠️ missing — install Node.js (for playwright)"
command -v ccc &>/dev/null && echo "cocoindex CLI (ccc): ✅" || echo "cocoindex CLI (ccc): ⚠️ optional — install via: pip install cocoindex"
# uvx-based: codebase-memory-mcp, code-review-graph, serena, cocoindex-code-mcp-server (available when uvx installed)

Report Format

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Codex Health — <repo>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  AGENTS.md budget         ✅ 187 lines / 4.2KB (budget: 32KB)
  config.toml              ✅ valid + schema directive
  hooks.json               ✅ valid JSON, 9 hooks registered
  Hook scripts             ✅ 9/9 executable
  Subagents                ✅ 5/5 complete
  Skills                   ✅ 30/30 have valid frontmatter
  Error log                ✅ CODEX_ERRORS.md exists
  Secrets scan             ✅ no leaks detected
  codebase-memory-mcp      ⚠️ missing — run setup-plugins.sh
  cocoindex (ccc)          ✅ installed
  code-review-graph        ✅ installed
  uvx (playwright/serena)  ✅ installed
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Overall: ⚠️ healthy with 1 warning
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

After the table, list any ⚠️/❌ items with one-line fix instructions.

Source: brain-bootstrap/codex-brain-bootstrap — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Security
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Node.js
Detected file/system behavior: Read-only
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview health-tomevault-io.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Health Skill — Codex Configuration Validation

Verify that the Codex Brain configuration is healthy and complete.

## Steps

### 1. AGENTS.md
- Exists and is not empty
- Line count: `wc -l < AGENTS.md`
- Size: `wc -c < AGENTS.md` (budget: ≤32KB = 32768 bytes)
- Contains key sections: Skills Roster, Exit Checklist, Terminal Rules

### 2. config.toml
- `.codex/config.toml` exists and is valid TOML
- Has `#:schema` directive on first line
- Has `codex_hooks = true` under `[features]`

### 3. hooks.json
- `.codex/hooks.json` exists and is valid JSON: `jq . .codex/hooks.json`
- Hook count: `jq '[.. | objects | select(has("command"))] | length' .codex/hooks.json`

### 4. Hook Scripts
- All `.codex/hooks/*.sh` files exist and are executable:
  ```bash
  for h in .codex/hooks/*.sh; do test -x "$h" || echo "NOT_EXEC: $h"; done
  ```

### 5. Subagents
- All `.codex/agents/*.toml` files exist
- Each has `name`, `description`, `developer_instructions` fields:
  ```bash
  for f in .codex/agents/*.toml; do grep -q 'developer_instructions' "$f" || echo "INCOMPLETE: $f"; done
  ```

### 6. Skills
- All `.agents/skills/*/SKILL.md` files exist
- Each has `name:` and `description:` in frontmatter:
  ```bash
  for f in .agents/skills/*/SKILL.md; do grep -q '^name:' "$f" || echo "BAD FRONTMATTER: $f"; done
  ```

### 7. Error Log
- `brain/tasks/CODEX_ERRORS.md` exists (warn if missing)

### 8. Secrets Scan
```bash
git ls-files | xargs grep -l 'BEGIN.*PRIVATE KEY\|password\s*=\s*[^{][^"\x27]\{8,\}' 2>/dev/null | head -10
```
Report any matches as ⚠️ warnings.

### 9. MCP Tool Reachability
Check that the required runtimes are available (all MCP tools run via `uvx` or `npx`):
```bash
command -v uvx &>/dev/null && echo "uvx: ✅" || echo "uvx: ❌ missing — install via: pip install uv"

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Steps → 1. AGENTS.md → 2. config.toml → 3. hooks.json → 4. Hook Scripts → 5. Subagents
terms    -> Verify that the Codex Brain configuration is healthy and complete. · After the table, list any ⚠️/❌ items with one-line fix instructions.
files/cmd -> wc -l < AGENTS.md · wc -c < AGENTS.md · .codex/config.toml · #:schema · codexhooks = true · [features] · .codex/hooks.json · jq . .codex/hooks.json
body sha256 -> e0a1bd57b867