lint

A command for checking a wiki for broken links, orphaned pages, outdated claims, contradictions, and inconsistent page metadata.

In plain words
What is it for?
Use it to audit all wiki pages or limit checks to concepts, source pages, or links. Run it with --fix when you want safe automatic corrections alongside a report.
Why use it?
It finds maintenance problems that are easy to miss when pages and links change over time. An optional fix mode applies only changes considered safe.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/capitalone/context-specs/lint
Clone the repo
git clone --depth 1 https://github.com/capitalone/context-specs
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.01728
Opus 5 $0.00020 $0.00864
Sonnet 5 $0.00008 $0.00346
Haiku 4.5 $0.00004 $0.00173

Measured 2d ago against content hash 42c0b412b79e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lint scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/human-loop/wiki-init/assets/commands/lint.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/lint

Read CLAUDE.md first for the layered structure, page taxonomy, frontmatter contract, and hard rules.

Arguments: $ARGUMENTS

Parse from $ARGUMENTS:

  • --scope=all|concepts|sources|links — narrow which checks run (default: all).
  • --fix — auto-apply safe fixes only (broken-link renames where the target is unambiguous, frontmatter normalization, trivial backlinks). All non-safe findings remain as suggestions in the report.

Walk wiki/ and read every markdown page. For each page extract:

  • Path, slug, frontmatter (type, title, created, updated, status, tags, sources, aliases, raw_path if source).
  • All [[wikilinks]] (outgoing edges).
  • Headers and section structure.

Build:

  • A slug → page map (note duplicate slugs across folders if any — that's a warning).
  • An alias map: alias → slug.
  • An adjacency list (outgoing) and reverse-adjacency (incoming = backlinks).

Step 2 — Run checks

Run these unless filtered out by --scope:

Broken links (scope: links or all)

For every [[target]] in every page, check target resolves to an existing slug or a known alias. If not, flag.

  • Safe-fix: if the target is a near-miss of exactly one existing slug (Levenshtein ≤ 2 or singular/plural mismatch), --fix rewrites the link.
  • Otherwise, suggest in the report.

Orphans (scope: concepts or all)

A page is an orphan if no other page links to it. Exclude wiki/MOC.md and pages under wiki/indexes/. Source-summary pages (type: source) are also exempt — they're entry points for raw content, not nodes the wiki is required to reach.

Missing backlinks (scope: links or all)

If page A's body or Related section links [[B]], and B's "Related" section does not mention [[A]], flag as a missing reciprocal link. Heuristic — surface for review.

  • Safe-fix: with --fix, append [[A]] to B's Related list if and only if both pages are concept/entity/workflow type and A is the only missing reciprocal.

Read the full file on GitHub · 150 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.

  1. 2d ago First seen · 150 lines · 0 tokens per session scan A 42c0b412b79e

Subscribe to this mod's changes

lint is a command published in the GitHub repository capitalone/context-specs (41 stars, last pushed 8d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,728 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.