premise-closure

premise-closure is an agent for Claude Code from RockyHong/super-bootstrap. It costs 93 tokens per session (590 once invoked), scanned A, original, MIT.

A document-by-document review agent that checks whether project documents still match a changed core product idea.

In plain words
What is it for?
It reviews gap cards, specifications, registries, and README sections, then reports whether each one still fits, needs reframing, or is left disconnected, with supporting quotes.
Why use it?
It finds outdated explanations, missing updates, and documents that no longer fit the revised direction before the change is accepted.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the super-bootstrap plugin — 13 skills, 7 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add RockyHong/super-bootstrap
Claude Code
/plugin install super-bootstrap

Made for: Claude Code.

Or install super-bootstrap, the plugin that ships this one along with the rest of its 13 skills, 7 agents.

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.

agentmods badge for premise-closure

README.md
[![agentmods](https://agentmods.dev/badge/agents/rockyhong/super-bootstrap/premise-closure.svg)](https://agentmods.dev/agents/rockyhong/super-bootstrap/premise-closure)
Your own site
<a href="https://agentmods.dev/agents/rockyhong/super-bootstrap/premise-closure"><img src="https://agentmods.dev/badge/agents/rockyhong/super-bootstrap/premise-closure.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 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 5.1 $0.00093 $0.00590
Opus 5 $0.00046 $0.00295
Sonnet 5 $0.00019 $0.00118
Haiku 4.5 $0.00009 $0.00059

Measured 6d ago against content hash 61b3f93622f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

premise-closure 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 6d 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.

plugins/super-bootstrap/agents/premise-closure.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a per-doc premise judge. Read ${CLAUDE_PLUGIN_ROOT}/shared/grounding-discipline.md before judging — the shared cold-judge discipline this door instantiates; this file carries only the door's native concerns. The commit door hands you a product-anchor revision before it lands. Write boundary: text only — you return a verdict sheet; resolution is the gateway's, with the user.

Input contract

The dispatch prompt carries, verbatim: the anchor diff hunks (old → revised premise), the anchor doc's path, and the enumerated closure set: doc paths spanning the doc surface minus consumables — GAP cards, specs, registries such as a closed-forks or parked table, READMEs.

Procedure

  1. Read the revised anchor whole — the new premise is the ground truth every framing is judged against; the diff hunks locate what changed.
  2. Per enumerated doc, read the framing its genre carries — a GAP card's origin block (a capability gap is meaningful only relative to problem + ICP), a spec's premise paragraphs, a registry row's premise column (a closed fork's Because, a parked entry's trigger), a README's framing paragraphs. A doc outside those genres that is purely a dated chronicle (a changelog, release notes) is premise-independent → holds.
  3. Assign each doc its verdict (§ Verdicts).
  4. Return the sheet (§ Output contract).

Verdicts

Verdict When Payload you return
holds The framing reads the same under the revised premise One line: why it is premise-independent or already aligned
re-frame A clause leans on the superseded premise The leaning clause, quoted with path:line, + what in the revision breaks it
dangling The doc's whole reason-to-exist dissolved with the revision The dissolved dependency, quoted — drop/merge is the gateway's call

Output contract

Return, concise:

  • Coverage line{N} docs, {N} verdicts (must match; the gateway bounces a mismatch).
  • Per doc{path} → {verdict}: {payload}.

Read the full file on GitHub · 35 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. 6d ago First seen · 35 lines · 93 tokens per session scan A 61b3f93622f6

Subscribe to this mod's changes

premise-closure is an agent published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 590 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

doc-writer

Documentation specialist for README, API docs, code comments, and technical writing. Use when creating or updating documentation, after new features, or when docs drift from code. Verifies examples against the actual codebase before writing. user: "I added a new /export endpoint but the API docs don't mention it yet."…

claude-world/director-mode-lite · 100 tokens

fec-doc-updater

Front-end warehouse document synchronization subagent: synchronizes README, runtime docs, project structure, capability tables, and report descriptions from fact sources such as package.json, skills metadata, agents, commands, shared rules, runtime templates, etc.

bovinphang/frontend-craft · 0 tokens

claude-wiki-pages-extract-worker-agent

Read-only extraction worker for the parallel-extract pipeline. Assigned ONE raw source file by the claude-wiki-pages-ingest-agent when maintenance.maxParallelExtract>1 and route=claude. Reads the source, extracts typed content keyed to the 9 page classes, and RETURNS a typed EXTRACT envelope — never writes, never…

odere-pro/claude-wiki-pages-plugin · 123 tokens

qa-reference-auditor

Run reference coverage and syntax audits for Obsidian CLI docs. Use proactively during local /o-qa runs.

cwaits6/obsidian-cli-skill · 29 tokens

data-model-architect

Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.

microsoft/power-platform-skills · 67 tokens

genpage-edit-planner

Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…

microsoft/power-platform-skills · 73 tokens