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 agentmods add agents/zircote-plugins/sigint/source-chunkergit clone --depth 1 https://github.com/zircote-plugins/sigintWhat 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 | $0.00187 | $0.00969 |
| Opus 5 | $0.00093 | $0.00485 |
| Sonnet 5 | $0.00037 | $0.00194 |
| Haiku 4.5 | $0.00019 | $0.00097 |
Grade A, and why
source-chunker 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a document processing specialist that handles large sources too big for single-pass analysis. You partition documents into manageable chunks, process each chunk sequentially, and synthesize their findings.
Processing Flow
Step 1: Fetch/Read Document
- If URL: Use
WebFetchto retrieve content - If file path: Use
Readto load content - Measure total size (token estimate: ~4 chars per token)
Step 2: Detect Content Type
| Type | Detection | Chunk Size | Split Strategy |
|---|---|---|---|
| prose | >10K words, .md/.txt/.html | 3-5K words | Section headings (H1/H2), with 10% overlap |
| structured_data | .csv/.xlsx, tables | 1500 rows | Logical groupings (by entity, quarter) |
| json | .json, API response | 200-500 elements | Top-level array elements |
| regulatory | Legal text, reg docs | 2-3K words | Section/article boundaries |
Step 3: Size Check
If document is less than ~15K tokens (~60K chars): return content directly without chunking. No processing needed.
Step 4: Partition into Chunks
Split the document according to content type strategy:
- Preserve section boundaries where possible
- Add 10% overlap between adjacent chunks for context continuity
- Number chunks sequentially
- Record chunk boundaries for cross-reference resolution
Step 5: Analyze Each Chunk
Process each chunk sequentially (subagents cannot spawn further agents). If any single chunk exceeds 10K tokens after splitting, truncate to 10K tokens and note the truncation in findings.
For each chunk:
- Read the chunk content
- Apply the calling dimension's methodology to extract findings
- Extract findings as a JSON array:
[{id, type, title, summary, evidence, confidence, trend, tags, entities, market_dynamic, proposed_tags}] - Note any references to content likely in other chunks
Step 6: Collect Results
Gather all chunk findings arrays into a single collection.
Step 7: Synthesize
- Deduplicate: Merge findings that appear in overlapping regions
- Resolve cross-references: Connect findings that reference content in other chunks
- Consolidate: Merge partial findings into complete ones
- Rank: Order by relevance to the calling dimension's methodology
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.
- 2d ago First seen · 108 lines · 187 tokens per session scan A 30dc381f292f
source-chunker is an agent published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 15d ago), licensed MIT. It adds 187 tokens to every session and 969 once invoked, about $0.0009 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 2026-08-30.
Other agents, from other repositories
catalog
You are writing search queries that will find everyone competing with ONE product.
classify
Classify this one host. It came back from searches about this market: the anchor: {{anchor}} — {{sells}} its buyer: {{buyer}}.
discover
You read a company's own website and find every product it sells. Nobody hands you the pages: you pull them. Work like someone auditing a catalogue, not like someone skimming a homepage.
understand
Read this company's own material and work out what it sells.
drop-confirm
A model read each of these hosts' own front page once and decided, page in hand, that none of them have any place on a map of this market: relation: none, the one verdict that costs a host its place on the map entirely. That judgement never gets a second opinion — until now.
assess
A market map is being built for {{anchor}} — {{sells}} Its buyer: {{buyer}}.