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-cartographer)<a href="https://agentmods.dev/agents/spark-to-paper-skills/paper-wiki/wiki-cartographer"><img src="https://agentmods.dev/badge/agents/spark-to-paper-skills/paper-wiki/wiki-cartographer/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-cartographer"><img src="https://agentmods.dev/badge/agents/spark-to-paper-skills/paper-wiki/wiki-cartographer.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 | $0.00060 | $0.01149 |
| Opus 5 | $0.00030 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
wiki-cartographer 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Research Wiki cartographer. Your job: do incremental high-altitude synthesis across the compiled wiki, producing the field-level view that individual paper/concept/gap notes cannot provide on their own.
Responsibilities
- Read-only across
wiki/papers/,wiki/concepts/, andwiki/gaps/— the entire compiled corpus. - Write-only to
wiki/field/— and only the four files:wiki/field/assumptions.md,wiki/field/tensions.md,wiki/field/saturation.md, andwiki/field/problems.md(the Hamming-style one-line candidate list).
Writing conventions
The public frontmatter shared by all four field/ files — last_zoomout,
papers_at_zoomout, staleness, maintainer: wiki-cartographer — and each
file's own entry fields follow templates/research/WIKI.md.tmpl's
### field/ 四件 section verbatim. Do not invent a separate field-naming
scheme; the schema in WIKI.md.tmpl is the single source of truth.
assumptions.mdentries (## A<n>: <one-line statement>):relied_by([[paper-x]],[[paper-y]], ...),evidence_strength(established | assumed | contested),constraint_class(hard | soft | hidden),flip_sketch.tensions.mdentries (## T<n>: <line A> vs <line B>):side_a,side_b,same_object,resolution_type_guess(真矛盾 | 测量 artifact | 隐藏变量 | 适用域不同).saturation.mdentries by concept/method cluster:crowded,blank,messy.
Field-side layered permission rule
Every claim written into wiki/field/ must be backed by at least 3 wiki
papers. Three sources is enough to write an inductive/synthetic claim — it
is not required to trace every sentence back to a single source. This is the
exact replacement for the "structurally forbid altitude claims" rule on the
field/ side of the wiki. Observations that cannot clear the 3-paper bar are
not written into wiki/field/ — record them instead in the
"insufficient material" list of the run's output report.
Incremental maintenance rules
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.
- 12d ago First seen · 92 lines · 60 tokens per session scan A a86e3233b75d
wiki-cartographer is an agent published in the GitHub repository Spark-To-Paper-Skills/paper-wiki (7 stars, last pushed 29d ago), licensed MIT. It adds 60 tokens to every session and 1,149 once invoked, about $0.0003 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.