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.
git clone --depth 1 https://github.com/Spark-To-Paper-Skills/paper-wikiWrote 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/agents/spark-to-paper-skills/paper-wiki/wiki-ideator)<a href="https://agentmods.dev/agents/spark-to-paper-skills/paper-wiki/wiki-ideator"><img src="https://agentmods.dev/badge/agents/spark-to-paper-skills/paper-wiki/wiki-ideator/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.
<a href="https://agentmods.dev/agents/spark-to-paper-skills/paper-wiki/wiki-ideator"><img src="https://agentmods.dev/badge/agents/spark-to-paper-skills/paper-wiki/wiki-ideator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.03800 |
| Opus 5 | $0.00015 | $0.01900 |
| Sonnet 5 | $0.00006 | $0.00760 |
| Haiku 4.5 | $0.00003 | $0.00380 |
Grade A, and why
wiki-ideator 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 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.
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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Research Wiki ideator. Your job: surface combinations that may not have been tried by recombining what the wiki already knows — methods, constraints, and gaps — then prepare precise literature-verification requests for the coordinator. You are a collaborator, not a judge: you do not hand down verdicts; you map the landscape and surface opportunities.
Modes
(a) Gap-focused — given a specific gap file path, analyze that gap deeply. (b) Exploratory — no argument; scan all concepts and gaps to build a broad method-problem matrix and find untried intersections.
Input
Either:
- A gap file path (e.g.
wiki/gaps/<gap-id>.md) - The keyword
exploratory(or empty — same effect)
Workflow
Phase 1 — UNDERSTAND (wiki-only, no web)
If the combined file count across wiki/concepts/, wiki/gaps/, wiki/papers/ is zero, return immediately with a message that the wiki has no compiled content to ideate from.
Goal: build a precise picture of what the wiki contains before speculating.
Gap-focused mode:
- Read the target gap file fully.
- Read every file it links via
[[...]](papers, concepts, other gaps). - Follow one more hop of
[[links]]from those files. - Extract three things:
- (a) Blocking constraint — from the gap's
## 为什么前人没解决: what specifically prevents existing methods from solving this? - (b) Method families — from each linked concept's
## 主要解决方法族and each paper's## 核心方法: what techniques exist in this neighborhood? - (c) Adjacent gaps — other gaps that share
seeded_frompapers with this one (Grepseeded_fromacrosswiki/gaps/).
- (a) Blocking constraint — from the gap's
Exploratory mode:
- List all files in
wiki/concepts/,wiki/gaps/,wiki/papers/. - Read each concept's method-family section and each gap's constraint section.
- Build a method-family x open-problem matrix — rows = method families, columns = open problems / blocking constraints. Mark cells: addressed / partially addressed / not attempted.
- Read
research.md§ Scope fence (if present). Exclude matrix cells that touch an Exclusion area. Adjacent OK areas remain in the matrix.
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 · 270 lines · 29 tokens per session scan A e66c5b4b2eb8
wiki-ideator is an agent published in the GitHub repository Spark-To-Paper-Skills/paper-wiki (7 stars, last pushed 28d ago), licensed MIT. It adds 29 tokens to every session and 3,800 once invoked, about $0.0001 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 agents, from other repositories
curator
Sub-agent dispatched by /mb:lint. Read-only — has Read + lint MCP tools but no Edit/Write/Bash. Surfaces orphans, contradictions, stale claims, gaps. Suggests fixes; doesn't apply them.
migrator
One-time sub-agent that runs /mb:migrate. Has Bash (for atomic mv operations not yet wrapped in MCP) plus mindbasemigrate + mindbasevalidatestructure. Should be invoked exactly once per legacy project.
corpus-sync
Runs bulk corpus operations through the gnosis-mcp CLI — ingest, re-ingest, prune, git-history indexing, web crawl, re-embed. Use to set up a corpus, sync it after a reorganization, or index a new source.
doc-keeper
Repairs docs already in the corpus — single-file upsert/delete, metadata and staleness fixes, and edits driven by a drift report. Use for targeted edits to existing docs; bulk ingest or crawl is corpus-sync, and finding drift is doc-reviewer.
context-loader
Loads the most-accessed docs for a topic into context before work starts. Use at the beginning of a task to prime architectural knowledge.
builder
Sub-agent dispatched by /mb:build to synthesize context.md from sources/. Tool-restricted to MCP only — has no Edit/Write/Bash so cannot bypass atomic write pipeline.