longform-discipline
v1.6.1Guardrails and a minimal working loop for co-writing a LONG document with an AI — tens of thousands of characters to book length, including academic long-form. Long documents fail by drifting rather than by being written badly, so this skill targets the three measured decay axes (long input, long output, long session) with rules that hold across whatever other skill is running: never single-pass the whole document, carry a spine file (purpose, outline, glossary, style contract, claims) outside the context window, write sections sequentially with the previous section's tail loaded, repair the seams that decomposition provably creates, keep the outline revisable, and gate on a deterministic scan plus a specific human review list rather than AI self-scoring. Every rule traces to a cited finding in references/failure-modes.md, including the disagreements. Ships a stdlib-only drift_scan.py that reads the spine and enforces it, now including an INTENT ledger — the exit condition written before the work, so a silent change of aim becomes visible instead of being noticed three sections later — and CONTENT checks that ask whether the draft does what the spine said it would (claim coverage, unverified claims, terms used before their definition, unsourced assertions), plus references/content-review.md — the per-section procedure that produces the human review list for what needs meaning. Surface checks: declared style-contract and glossary violations, cross-section contradiction of typed facts (numbers, dates, versions, 可否) plus a ledger-driven candidate list that narrows what a human must read side by side, 文体 mixing, over-long sentences, notation drift, cross-section duplication, and section-length collapse — with exit codes suitable as a loop's stop condition, plus an optional SudachiPy backend that lifts terminology-drift recall from 0/8 to 6/8 on unlisted variants. Bilingual JA/EN, with Japanese long-form rules sourced from 文化審議会建議「公用文作成の考え方」and the JTF style guide.
By dobachi0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Aug 30, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install plugin
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install longform-discipline@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/dobachi/claude-skills-marketplaceClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/longform-discipline/.
Plugin files
├── .claude-plugin/plugin.json└── skills/longform-discipline/SKILL.md
Included Skills1
Guardrails and a minimal loop for co-writing a LONG document with an AI — tens of thousands of characters to book length, including academic long-form. Long documents fail by drifting — the terminology moves, and so does the aim. You set out to strengthen an argument and five turns later you are polishing wording, with nothing announcing the change. So write the exit condition before the work, keep a spine file (intent ledger, outline, glossary, style contract, claims) outside the context window, never single-pass, write sections sequentially, repair the seams decomposition creates, and gate on a deterministic scan plus a human review list, not AI self-scoring. drift_scan.py checks intent, content and surface; content-review.md is the procedure for what needs meaning. Bilingual JA/EN. 長文, 長編, 章立て, 数万字, 書籍, whitepaper, thesis — 用語がぶれる / 章がちぐはぐ / 後半が薄い / 主旨がすり替わる. Hands critique to doc-review, facts to verify-content.
Plugin manifests1
{
"name": "longform-discipline",
"description": "Guardrails and a minimal working loop for co-writing a LONG document with an AI — tens of thousands of characters to book length, including academic long-form. Long documents fail by drifting rather than by being written badly, so this skill targets the three measured decay axes (long input, long output, long session) with rules that hold across whatever other skill is running: never single-pass the whole document, carry a spine file (purpose, outline, glossary, style contract, claims) outside the context window, write sections sequentially with the previous section's tail loaded, repair the seams that decomposition provably creates, keep the outline revisable, and gate on a deterministic scan plus a specific human review list rather than AI self-scoring. Every rule traces to a cited finding in references/failure-modes.md, including the disagreements. Ships a stdlib-only drift_scan.py that reads the spine and enforces it, now including an INTENT ledger — the exit condition written before the work, so a silent change of aim becomes visible instead of being noticed three sections later — and CONTENT checks that ask whether the draft does what the spine said it would (claim coverage, unverified claims, terms used before their definition, unsourced assertions), plus references/content-review.md — the per-section procedure that produces the human review list for what needs meaning. Surface checks: declared style-contract and glossary violations, cross-section contradiction of typed facts (numbers, dates, versions, 可否) plus a ledger-driven candidate list that narrows what a human must read side by side, 文体 mixing, over-long sentences, notation drift, cross-section duplication, and section-length collapse — with exit codes suitable as a loop's stop condition, plus an optional SudachiPy backend that lifts terminology-drift recall from 0/8 to 6/8 on unlisted variants. Bilingual JA/EN, with Japanese long-form rules sourced from 文化審議会建議「公用文作成の考え方」and the JTF style guide.",
"version": "1.6.1",
"author": {
"name": "dobachi"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[longform-discipline on Agent Plugins Marketplace](https://pluginsmp.com/plugins/longform-discipline)