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.
npx skills add queelius/claude-anvil --skill cross-reference-disciplinegit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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.
[](https://agentmods.dev/skills/queelius/claude-anvil/cross-reference-discipline)<a href="https://agentmods.dev/skills/queelius/claude-anvil/cross-reference-discipline"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/cross-reference-discipline.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.00977 |
| Opus 5 | $0.00024 | $0.00489 |
| Sonnet 5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
cross-reference-discipline 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-reference Discipline (bookwright)
LaTeX cross-references are mechanical. The trouble with them is that LaTeX silently emits "Reference undefined" warnings without erroring out, and over a long manuscript a single typo can cascade into chapters of broken refs that nobody notices. This skill encodes the discipline that prevents that.
Header comment block (every section)
Every section file starts with a comment block. Template:
% §X.Y Section Title
%
% Cross-reference resolution status:
%
% DEFINED here: labels this section creates.
% \label{sec:foo}
% \label{def:bar}
% \label{thm:baz}
%
% RESOLVED (chapter X):
% \Cref{sec:foo-prior} -- file: book/chapters/chXX/foo.tex
% \Cref{def:bar-prior} -- file: book/chapters/chXX/bar.tex
%
% FORWARD REFS (resolve in later sections/chapters):
% \Cref{sec:foo-future} -- target: ch. Y §Y.Z (this plan's Task N)
% \Cref{ch:future-chapter} -- target: ch. Z (drafted in a future plan)
Why: the cross-ref-auditor and the integration check both read these blocks. The comment is the section's contract with the rest of the book.
Label naming conventions
sec:foo-bar: section labels (kebab-case after the type prefix).def:foo-bar: definitions.prop:foo-bar: propositions.thm:foo-bar: theorems.cor:foo-bar: corollaries.lem:foo-bar: lemmas.eq:foo-bar: display equations.tab:foo-bar: tables.fig:foo-bar: figures.alg:foo-bar: algorithms.ex:chN-M: exercises (chapter N, exercise number M).ch:foo-bar: chapters.
Label names should be the section/concept name in kebab-case. Avoid generic names like sec:intro or def:1 that collide across chapters.
When to use \Cref vs prose-only
- Use
\Cref{...}when the target label EXISTS at build time. - Use prose-only (e.g., "chapter 17 covers this") when:
- The target chapter is not yet drafted (Plan 0 stubs aside).
- The reference is informal ("the next chapter," "the appendix").
- The reference is to an external paper (use
\cite{}instead).
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.
- 7d ago First seen · 82 lines · 49 tokens per session scan A f8b8a7e5191c
cross-reference-discipline is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 977 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 2026-08-31.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.