A structural checker for a knowledge vault, which is a linked collection of notes about entities such as papers, concepts, people, claims, and experiments. It validates required fields, allowed values, links, graph edges, and optional lens-specific rules.

Use it to validate the vault, produce machine-readable results, preview or apply safe fixes, check an aesthetic or general analysis lens, and rebuild the graph when requested.

It finds broken links, missing information, stale references, and inconsistencies before other commands or a release use the vault. It can also show suggested repairs and optionally apply deterministic fixes.

How P1-103n1x/bab-ilu configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to P1-103n1x/bab-ilu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/P1-103n1x/bab-ilu/v2.2-oss-public/.claude/skills/lint/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/P1-103n1x/bab-ilu

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/lint/github.svg)](https://agentmods.dev/skills/p1-103n1x/bab-ilu/lint)

Your own site

<a href="https://agentmods.dev/skills/p1-103n1x/bab-ilu/lint"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/lint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/p1-103n1x/bab-ilu/lint"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,499 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.02499
Opus 5	$0.00033	$0.01249
Sonnet 5	$0.00013	$0.00500
Haiku 4.5	$0.00007	$0.00250

Measured 11d ago against content hash fcdee90f3479, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lint scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Delegates to `tools/graph_analyzer.py` via `subprocess.run`. The analyzer

.claude/skills/lint/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/lint — Vault structural + lens-aware validator (v2.1)

Synopsis

/lint                                            # v2.0 entity checks only
/lint --lens=aesthetic-warburg                   # + anchor + tier consistency
/lint --lens=general-zettelkasten --json         # machine-readable output
/lint --fix                                      # auto-fix deterministic issues
/lint --fix --dry-run                            # preview fixes only
/lint --rebuild-graph --lens=aesthetic-warburg   # re-run graph_analyzer after lint
/lint --suggest                                  # show remediation hints for non-fixable

What this skill does

/lint is the vault's structural gatekeeper. It runs before /prompt, before /distill, and before any release to catch broken links, missing fields, stale cross-references, and (when a lens is active) lens-specific drift.

Four layers of checks run in order:

v2.0 entity checks — always on. Validates papers/, concepts/, topics/, people/, ideas/, experiments/, claims/, foundations/ per tools/_schemas.py (required fields, enum values, idea/experiment completeness, xref symmetry, graph edge consistency, content quality).
Karpathy active-suggestion checks (K2, Sprint 4; PRD §0.5.4) — always on, lens-agnostic parts. Structural MVP — LLM-backed tiers defer to Sprint 5 per principle 1 (late binding):
- stale-claim — pages citing a target whose slug appears as the to of any [[x]] [retracts-<code>] [[target]] line in .agent/graph/*.md. Per .agent/spec/gap-algorithm.md §2.
- material-request — a missing wikilink target referenced by ≥ 2 distinct pages. Below 2 references is ordinary broken-link noise; at 2+ the wiki itself is asking for a page on that slug.
Lens-aware checks — opt-in via --lens <id>. Adds:
- lens-anchor — tier-0 pages missing every authority field the lens declares in anchors.authority_fields. Lenses without anchors (e.g. zettelkasten) silently skip this check.
- lens-tier — tier-1-cluster pages whose wikilinks resolve to EXISTING pages of the wrong type. Broken-target wikilinks are intentionally not double-reported here — check_broken_links already covers them.
- contradiction (K2 Rule A, Sprint 4) — same normalized title across ≥ 2 pages with mismatched values for the lens's anchors.authority_fields. Lenses without authority fields (e.g. zettelkasten) silently skip. Severity 🟡 — users decide whether to reconcile, add a contradicts edge, or mark as intentional.
Graph rebuild — opt-in via --rebuild-graph. After lint completes (and after --fix if requested), delegates to tools/graph_analyzer.py as a subprocess, forwarding --lens and --lenses-base unchanged.

Read the full file on GitHub · 221 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 221 lines · 66 tokens per session scan A fcdee90f3479

Subscribe to this mod's changes

lint is a skill published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 2,499 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Databases Debugging

fix-failing-tests

Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…

googleapis/mcp-toolbox · 87 tokens

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens

postgresql-indexing

PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…

prowler-cloud/prowler · 108 tokens

bab-ilu: Skill for Claude Code