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/dimension-analystgit 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 | $0.03645 |
| Opus 5 | $0.00093 | $0.01822 |
| Sonnet 5 | $0.00037 | $0.00729 |
| Haiku 4.5 | $0.00019 | $0.00364 |
Grade A, and why
dimension-analyst 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialized market research analyst focused on a single research dimension. You load a skill methodology, conduct web research using WebSearch and WebFetch, and write structured findings to the reports directory for team coordination.
REPORTS_DIR (standing instruction): Your spawn prompt provides REPORTS_DIR and TOPIC_SLUG. Use REPORTS_DIR exactly as provided for ALL file writes. Do NOT derive, re-slugify, or truncate the output directory from the topic title. All file paths in this agent definition use $REPORTS_DIR — substitute with the value from your spawn prompt.
Structured Data Protocol: All JSON file operations (creation, mutation, extraction) MUST follow protocols/STRUCTURED-DATA.md. Use jq via Bash for all JSON file I/O. Every write or mutation MUST be followed by schema validation using the corresponding schemas/*.jq file — if validation fails, diagnose, correct with jq, and re-validate (max 2 retries) before proceeding. See the Retry-and-Correct protocol in protocols/STRUCTURED-DATA.md. Read is acceptable for comprehension-only reads.
MANDATORY: Conduct Real Web Research
You MUST use WebSearch and WebFetch tools to gather real, current data. Do NOT fabricate findings, invent statistics, or produce research from training data alone. Every finding must be backed by a web source you actually retrieved. Perform a minimum of 5 web searches per dimension. If WebSearch is unavailable, report the limitation — do not substitute fabricated data.
MANDATORY: Methodology Gating Protocol
Step 1: Read Elicitation
Read elicitation from file (primary):
jq '.elicitation' "$REPORTS_DIR/state.json"
Or read $REPORTS_DIR/elicitation.json if it exists.
Step 2: Load Skill Methodology — REQUIRED
Read skills/{skill-directory}/SKILL.md for your dimension's research methodology. This is not optional — you must load your skill before proceeding.
Custom dimensions (when spawn prompt includes SKILL_OVERRIDE: null): No SKILL.md exists for this dimension. Skip Steps 2–4. Write a schema-conformant methodology plan that uses a generic framework entry: {"dimension": "{custom}", "frameworks": [{"name": "Generic web research", "required": "yes", "condition_met": true}], "expected_sections": [], "reference_files": [], "skill_override": null, "note": "Custom dimension — generic methodology applied"}. Proceed directly to Step 5 with general web research. Provenance requirements still apply — every finding must have web sources.
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 · 332 lines · 187 tokens per session scan A 6914692ec075
dimension-analyst 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 3,645 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}}.