Agent skill

Healthcheck

by iurykrieger in iurykrieger/claude-bedrock

Read-only vault health diagnostic. An agent skill from iurykrieger/claude-bedrock.

MITAuto-check: notesKnowledge Management

Install Healthcheck

skills CLI
$ npx skills add iurykrieger/claude-bedrock --skill healthcheck -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install iurykrieger/claude-bedrock healthcheck --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/iurykrieger/claude-bedrock.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/healthcheck .claude/skills/healthcheck && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
healthcheck
GitHub stars
105
Used in
1 other repo
Token cost
~3.7k tokens
SKILL.md length
1,504 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Read-only vault health diagnostic. An agent skill from iurykrieger/claude-bedrock.

  • Works in 3 steps: Scan the Vault → Run Checks → Generate Report
  • : bedrock healthcheck
  • SKILL.md covers Plugin Paths, Vault Resolution, Overview and Phase 1 — Scan the Vault, plus 4 more sections
  • Calls python3

What it does

Healthcheck is an agent skill from iurykrieger/claude-bedrock. Read-only vault health diagnostic. Generates a report without modifying any files. Checks: graphify-out integrity, setup verification, orphan entities, dangling content, old content (15 days). Safe to run at any frequency. Use when: "bedrock healthcheck", "bedrock-healthcheck", "vault health", "check vault", "vault status", "/bedrock:healthcheck".

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management. It works with Obsidian. The repository describes itself as: Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills. The licence is MIT.

When your agent uses it

  • : bedrock healthcheck
  • Bedrock-healthcheck
  • /bedrock:healthcheck

Example prompts

  • “bedrock healthcheck”
  • “bedrock-healthcheck”
  • “vault health”
  • “/healthcheck”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Scan the Vault
  2. Run Checks
  3. Generate Report

What it can do on your machine

Read from SKILL.md and the folder at commit 7cac16c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Healthcheck loads about 3.7k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 1,504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Glob, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from iurykrieger/claude-bedrock at commit 7cac16c, republished under its MIT licence (© iurykrieger). 1,504 words, ~3,664 tokens.

Download SKILL.mdSave it as .claude/skills/healthcheck/SKILL.md (or your agent's skills folder).
name
healthcheck
description
Read-only vault health diagnostic. Generates a report without modifying any files. Checks: graphify-out integrity, setup verification, orphan entities, dangling content, old content (>15 days). Safe to run at any frequency. Use when: "bedrock healthcheck", "bedrock-healthcheck", "vault health", "check vault", "vault status", "/bedrock:healthcheck".
allowed-tools
Bash, Read, Glob, Grep
user_invocable
true

/bedrock:healthcheck — Vault Health Report

Plugin Paths

Entity definitions and templates are in the plugin directory, not the vault root. Use the "Base directory for this skill" provided at invocation to resolve paths:

  • Entity definitions: <base_dir>/../../entities/
  • Templates: <base_dir>/../../templates/{type}/_template.md
  • Plugin CLAUDE.md: <base_dir>/../../CLAUDE.md (already injected automatically into context)

Where <base_dir> is the path provided in "Base directory for this skill".


Vault Resolution

Resolve which vault to diagnose. This skill can be invoked from any directory.

Step 1 — Parse --vault flag: Check if the input arguments include --vault <name>. If found, extract the vault name.

Step 2 — Resolve vault path:

  1. If --vault <name> was provided: Read the vault registry at <base_dir>/../../vaults.json. Find the entry matching the name. If not found: error — "Vault <name> is not registered. Run /bedrock:vaults to see available vaults." If found: set VAULT_PATH to the entry's path value.

  2. If no --vault flag — CWD detection: Read <base_dir>/../../vaults.json. Check if the current working directory is inside any registered vault path (CWD starts with a registered vault's absolute path). If multiple match, use the longest path (most specific). If found: set VAULT_PATH to the matching vault's path.

  3. If CWD detection fails — default vault: From the registry, find the vault with "default": true. If found: set VAULT_PATH to the default vault's path.

  4. If no resolution: Error — "No vault resolved. Available vaults:" followed by the registry listing. "Use --vault <name> to specify, or run /bedrock:setup to register a vault."

Step 3 — Validate vault path:

bash
test -d "<VAULT_PATH>" && echo "exists" || echo "missing"

If missing: error — "Vault path <VAULT_PATH> does not exist on disk. Run /bedrock:setup to re-register."

Step 4 — Read vault config:

bash
cat <VAULT_PATH>/.bedrock/config.json 2>/dev/null

Extract language and other relevant fields for use in later phases.

From this point forward, ALL vault file operations use <VAULT_PATH> as the root.

  • Entity directories: <VAULT_PATH>/actors/, <VAULT_PATH>/people/, etc.
  • Graphify output: <VAULT_PATH>/graphify-out/

Overview

This skill produces a diagnostic report of vault health without modifying any files. It scans the vault once, runs 5 checks against the scan data, and prints the results.

You are a read-only agent. You do NOT write files, commit, push, invoke other skills, or spawn subagents. Your only output is the diagnostic report printed to the terminal.

Five health checks
#CheckWhat it verifies
1graphify-outGraph.json exists, is valid, is fresh
2SetupDirectories, templates, entity definitions, plugin manifest
3Orphan entitiesEntities with zero inbound wikilinks
4Dangling contentEntities fully disconnected (no inbound, no outbound, no relations)
5Old contentEntities with updated_at older than 15 days
Status values

Each check reports one of:

  • OK — no issues found
  • WARN — issues found (with details)
  • MISSING — prerequisite not met (e.g., graphify-out absent)

Phase 1 — Scan the Vault

Read all entity files once and store the data for use across all 5 checks.

1.1 Enumerate entity files

For each entity directory (<VAULT_PATH>/actors/, <VAULT_PATH>/people/, <VAULT_PATH>/teams/, <VAULT_PATH>/concepts/, <VAULT_PATH>/topics/, <VAULT_PATH>/discussions/, <VAULT_PATH>/projects/, <VAULT_PATH>/fleeting/):

  1. List all .md files using Glob, excluding _template.md and _template_node.md
    • For actors: include both <VAULT_PATH>/actors/*.md (flat) and <VAULT_PATH>/actors/*/*.md (folder)
    • Include code entities: <VAULT_PATH>/actors/*/nodes/*.md
  2. Record the directory and filename for each entity
1.2 Read entity data

For each entity file found in 1.1:

  1. Read the file
  2. Extract from frontmatter:
    • type
    • name (or derive from filename)
    • aliases (array)
    • updated_at (date string)
    • All frontmatter array fields that contain wikilinks (e.g., actors, people, teams, related_to, etc.)
  3. Extract from body:
    • All wikilinks [[target]] (regex: \[\[([^\]]+)\]\])
  4. Compute:
    • outbound_wikilinks: union of all wikilinks from body + frontmatter arrays
    • has_frontmatter_relations: true if any frontmatter array field contains at least one wikilink value
    • entity_slug: the filename without extension (used as the canonical identifier)

Output: vault_entities map: entity_slug → {type, name, aliases[], updated_at, outbound_wikilinks[], has_frontmatter_relations, file_path}

Also collect: all_entity_slugs — set of all entity slugs in the vault (for resolving wikilinks).


Phase 2 — Run Checks

2.1 Check 1 — graphify-out
  1. Check if directory <VAULT_PATH>/graphify-out/ exists:

    bash
    ls -d <VAULT_PATH>/graphify-out/ 2>/dev/null && echo "EXISTS" || echo "MISSING"
  2. If MISSING:

    • Status: MISSING
    • Details: "graphify-out/ directory not found. Run /bedrock:learn on an actor repository to generate."
    • Skip remaining sub-checks.
  3. If EXISTS, check <VAULT_PATH>/graphify-out/graph.json:

    bash
    test -f <VAULT_PATH>/graphify-out/graph.json && echo "EXISTS" || echo "MISSING"
  4. If graph.json MISSING:

    • Status: MISSING
    • Details: "graph.json not found in graphify-out/. Run /bedrock:learn to generate."
    • Skip remaining sub-checks.
  5. If graph.json EXISTS, validate and extract stats:

    bash
    python3 -c "
    import json, os, time
    from pathlib import Path
    
    g = json.loads(Path('<VAULT_PATH>/graphify-out/graph.json').read_text())
    nodes = g.get('nodes', [])
    code_nodes = [n for n in nodes if n.get('file_type') == 'code']
    mtime = os.path.getmtime('<VAULT_PATH>/graphify-out/graph.json')
    mod_date = time.strftime('%Y-%m-%d', time.localtime(mtime))
    days_old = (time.time() - mtime) / 86400
    
    print(f'total_nodes={len(nodes)}')
    print(f'code_nodes={len(code_nodes)}')
    print(f'mod_date={mod_date}')
    print(f'days_old={int(days_old)}')
    print(f'stale={\"yes\" if days_old > 30 else \"no\"}')
    " 2>/dev/null || echo "INVALID_JSON"
  6. If INVALID_JSON:

    • Status: WARN
    • Details: "graph.json exists but is not valid JSON."
  7. If valid:

    • If stale (>30 days): Status: WARN, Details: "Graph.json is stale (>30 days). Last updated: {mod_date}. Run /bedrock:learn or /bedrock:sync to update."
    • If fresh: Status: OK, Details: "{total_nodes} nodes ({code_nodes} code). Last updated: {mod_date}."

Store: graphify_status, graphify_details, graphify_node_count

2.2 Check 2 — Setup

Verify the vault structure and plugin dependencies.

2.2.1 Entity directories

Check that each expected directory exists:

  • <VAULT_PATH>/actors/, <VAULT_PATH>/people/, <VAULT_PATH>/teams/, <VAULT_PATH>/concepts/, <VAULT_PATH>/topics/, <VAULT_PATH>/discussions/, <VAULT_PATH>/projects/, <VAULT_PATH>/fleeting/

For each directory, check if _template.md exists inside it.

Record: list of missing directories, list of directories missing templates.

2.2.2 Entity definitions

Check that entity definitions exist in the plugin directory:

<base_dir>/../../entities/

Expected files: actor.md, person.md, team.md, concept.md, topic.md, discussion.md, project.md, fleeting.md

Record: list of missing entity definitions.

2.2.3 Plugin manifest

Check that .claude-plugin/plugin.json exists and is valid JSON:

bash
python3 -c "import json; json.loads(open('.claude-plugin/plugin.json').read()); print('VALID')" 2>/dev/null || echo "INVALID"

Record: manifest status.

2.2.4 Result
  • If everything present: Status: OK, Details: "All directories, templates, definitions, and manifest verified."
  • If issues found: Status: WARN, Details: list of missing items.

Store: setup_status, setup_details, setup_issue_count

Show full SKILL.md (658 more words)Show less
2.3 Check 3 — Orphan entities

For each entity in vault_entities:

  1. Count inbound wikilinks: how many OTHER entities reference this entity via [[entity_slug]]
    • Search: count how many entities in vault_entities have this entity's slug in their outbound_wikilinks
    • Also check for alias matches: if entity has aliases, check if any alias (converted to slug format) appears in other entities' outbound wikilinks
  2. If inbound count = 0: mark as orphan

Exclude from orphan check:

  • Templates (_template.md)
  • The entity itself (self-links don't count)

Store: orphan_entities[] — list of {entity_slug, type} Aggregate: orphan_count_by_type — map type → count

Result:

  • If 0 orphans: Status: OK
  • If orphans found: Status: WARN, Details: count per type + entity names
2.4 Check 4 — Dangling content

From the orphan list (Check 3), further filter for entities that are fully disconnected:

An entity is dangling if ALL three conditions are true:

  1. No inbound wikilinks (already orphan from Check 3)
  2. No outbound wikilinks in the body (entity's outbound_wikilinks is empty)
  3. No frontmatter relations (entity's has_frontmatter_relations is false)

Store: dangling_entities[] — list of {entity_slug, type}

Result:

  • If 0 dangling: Status: OK
  • If dangling found: Status: WARN, Details: entity names
2.5 Check 5 — Old content

For each entity in vault_entities:

  1. Read updated_at from the entity data
  2. If updated_at is missing or cannot be parsed: skip (do not flag — missing metadata is a setup issue, not a staleness issue)
  3. Calculate age in days: current_date - updated_at
  4. If age > 15 days: mark as old

Store: old_entities[] — list of {entity_slug, type, updated_at, age_days}, sorted by age_days descending (oldest first) Aggregate: old_count_by_type — map type → count

Result:

  • If 0 old: Status: OK
  • If old found: Status: WARN, Details: count per type, oldest entity with age

Phase 3 — Generate Report

Print the full report to the terminal.

markdown
## /bedrock:healthcheck — Report

| Check | Status | Count | Details |
|---|---|---|---|
| graphify-out | {graphify_status} | {node_count} nodes | {graphify_details} |
| Setup | {setup_status} | {setup_issue_count} issues | {setup_details} |
| Orphan entities | {orphan_status} | {orphan_count} orphans | {orphan_details} |
| Dangling content | {dangling_status} | {dangling_count} dangling | {dangling_details} |
| Old content (>15d) | {old_status} | {old_count} stale | {old_details} |
Orphan details (if WARN)
markdown
### Orphan Entities

| # | Entity | Type |
|---|---|---|
| 1 | [[entity-slug]] | actor |
| 2 | [[entity-slug]] | person |
| ... | ... | ... |

**By type:** actors: N, people: N, teams: N, ...
Dangling details (if WARN)
markdown
### Dangling Content (fully disconnected)

| # | Entity | Type |
|---|---|---|
| 1 | [[entity-slug]] | fleeting |
| ... | ... | ... |
Old content details (if WARN)
markdown
### Old Content (>15 days without update)

| # | Entity | Type | Last updated | Age |
|---|---|---|---|---|
| 1 | [[entity-slug]] | actor | 2026-03-01 | 45 days |
| 2 | [[entity-slug]] | topic | 2026-03-15 | 31 days |
| ... | ... | ... | ... | ... |

**By type:** actors: N, topics: N, ...
Suggestions

Based on findings, append actionable suggestions:

  • If orphan or dangling count > 0: "Run /bedrock:compress to detect and fix alignment issues (broken backlinks, missing entities)."
  • If graphify-out is MISSING or stale: "Run /bedrock:learn on an actor repository to generate or update the graph."
  • If old count > 0: "Review {N} stale entities for relevance. Consider updating or archiving."
  • If setup has issues: "Run /bedrock:setup to initialize missing directories or templates."
  • If all checks are OK: "Vault is healthy. No action needed."

Error Handling

SituationAction
Empty vault (no entity files)Report all checks as OK with 0 counts. "Vault is empty — no entities found."
Entity file cannot be readSkip entity, do not fail the check. Note in report: "N entities skipped due to read errors."
Frontmatter cannot be parsedSkip entity for frontmatter-dependent checks (updated_at, relations). Count as readable for wikilink checks.
graphify-out/graph.json is not valid JSONReport as WARN for Check 1. Continue with other checks.
Plugin directory not accessibleReport as WARN for Check 2. Continue with other checks.
No updated_at field in entitySkip for Check 5 (old content). Do not flag as old.

Critical Rules

RuleDetail
Read-onlyNEVER use Write, Edit, Skill, or Agent tools. This skill only reads and reports.
No git operationsNEVER run git add, commit, push, pull, or any mutating git command.
No skill invocationsNEVER invoke /bedrock:compress, /bedrock:learn, /bedrock:preserve, or any other skill. Suggest them in text only.
Terminal output onlyThe report is printed to the terminal. No files are created or modified.
Single-pass scanPhase 1 scans once. All 5 checks in Phase 2 use the same scan data.
Exclude templatesAlways exclude _template.md and _template_node.md from entity counts and checks.
15-day thresholdOld content is defined as updated_at > 15 days from current date. Hardcoded.
30-day thresholdStale graph is defined as graph.json modification date > 30 days. Hardcoded.
Bare wikilinksParse wikilinks as [[name]] only. Never path-qualified ([[dir/name]]).
Sensitive dataNEVER include credentials, tokens, passwords, PANs, CVVs in the report.
Vault resolution firstResolve VAULT_PATH before any file operation — never assume CWD is the vault
All entity paths use <VAULT_PATH>/ prefix<VAULT_PATH>/actors/, not actors/

© iurykrieger, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/healthcheck of iurykrieger/claude-bedrock.

Open the folder on GitHubat commit 7cac16c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in iurykrieger/claude-bedrock, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Healthcheck next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Healthcheck compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Healthcheck this skilliurykrieger/claude-bedrock1051 repos~3.7kAutomated safety check: NotesMIT
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Second BrainNicholasSpisak/second-brain737—~1.5kAutomated safety check: NotesNone
Codex History IngestAr9av/obsidian-wiki3.5k—~2.2kAutomated safety check: NotesMIT

Similar skills

  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed
  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Second Brain

    NicholasSpisak/second-brain

    Set up a new Obsidian knowledge base with the LLM Wiki pattern.

    737 GitHub stars~1.5k tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check: notes
  • Codex History Ingest

    Ar9av/obsidian-wiki

    Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.

    3.5k GitHub stars~2.2k tokensUpdated today
    Knowledge ManagementAuto-check: notes
  • Autograph

    smixs/agent-second-brain

    Schema-as-code enforcement for any Obsidian vault. An agent skill from smixs/agent-second-brain.

    393 GitHub stars~3.7k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

More from iurykrieger/claude-bedrock

All 10 skills in this repo
  • Confluence To Markdown

    iurykrieger/claude-bedrock

    Internal fetcher module for Confluence pages. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check: notes
  • Gdoc To Markdown

    iurykrieger/claude-bedrock

    Internal fetcher module for Google Docs and Sheets. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~3.8k tokens
    Auto-check: notes
  • Vaults

    iurykrieger/claude-bedrock

    Manage registered Bedrock vaults. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check: notes
  • Setup

    iurykrieger/claude-bedrock

    Initialize any folder as a Bedrock-powered Obsidian vault. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~11k tokens
    Auto-check: notes
  • Compress

    iurykrieger/claude-bedrock

    Vault alignment engine. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~9.9k tokens
    Auto-check: warnings
  • Sync

    iurykrieger/claude-bedrock

    Re-synchronizes the vault with external sources. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~11k tokens
    Auto-check: warnings

Works with

Questions about Healthcheck

What does Healthcheck do?

Read-only vault health diagnostic. An agent skill from iurykrieger/claude-bedrock. Healthcheck is an agent skill from iurykrieger/claude-bedrock. Read-only vault health diagnostic.

When should I use Healthcheck?

Healthcheck fits situations like: : bedrock healthcheck; bedrock-healthcheck; /bedrock:healthcheck.

How do I install Healthcheck in Claude Code?

Run `npx skills add iurykrieger/claude-bedrock --skill healthcheck -a claude-code`. Or copy the skill folder (skills/healthcheck in iurykrieger/claude-bedrock) into .claude/skills/healthcheck in your project. Claude Code loads it when a task matches its description.

How do I install Healthcheck in Codex?

Run `npx skills add iurykrieger/claude-bedrock --skill healthcheck -a codex`. Or copy the skill folder (skills/healthcheck in iurykrieger/claude-bedrock) into .agents/skills/healthcheck in your project. Codex loads it when a task matches its description.

Can I use Healthcheck in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iurykrieger/claude-bedrock --skill healthcheck -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/healthcheck, .gemini/skills/healthcheck, .github/skills/healthcheck and .opencode/skills/healthcheck in your project.

What does Healthcheck need to run?

Going by SKILL.md and its folder, Healthcheck needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Glob, Grep.

Does Healthcheck access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Healthcheck safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Healthcheck use?

Healthcheck is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Healthcheck use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Healthcheck?

Skills that share tags, products or a category with Healthcheck: Obsidian CLI (Atmosphere/atmosphere, 3.8k stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Second Brain (NicholasSpisak/second-brain, 737 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Healthcheck?

iurykrieger (a GitHub user) maintains it in iurykrieger/claude-bedrock, which has 105 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on May 5, 2026.

Source: iurykrieger/claude-bedrock on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.