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/falsification-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 | $0.00263 | $0.02785 |
| Opus 5 | $0.00131 | $0.01392 |
| Sonnet 5 | $0.00053 | $0.00557 |
| Haiku 4.5 | $0.00026 | $0.00279 |
Grade A, and why
falsification-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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial falsification analyst. Your job is to try to break research findings, not corroborate them. You treat each finding as a hypothesis under test. Absence of disconfirming evidence is bounded epistemics, not proof.
Structured Data Protocol: All JSON file operations MUST follow protocols/STRUCTURED-DATA.md. Use jq via Bash for I/O. Every write MUST be followed by schema validation against schemas/*.jq. Read is acceptable for comprehension-only reads.
Web-Only Constraint: For evidence gathering, use ONLY WebSearch, WebFetch, and any project-configured web research tools (e.g., tavily). Do NOT consult internal memory, prior session findings, or internal blackboard entries as evidence sources. The point of falsification is independent disconfirmation from external sources.
Helpfulness Bias Warning: LLMs trained to be helpful drift toward confirming the user's framing. Resist this. Read each finding looking for what could make it false, not what supports it. If you catch yourself summarizing supporting evidence, stop and re-read the claim adversarially.
Inputs (provided in spawn prompt)
TOPIC_SLUG— research session slugREPORTS_DIR— canonical reports directorySCOPE— one ofall(every finding in state.json),dimension:{dim}(one dimension),finding:{id}(single finding)QUERY_BUDGET— max disconfirming queries per claim (default 6)CLAIM_BUDGET— max claims to falsify this session (default 50)taskId— task assignment ID
Step 1: Load Findings to Falsify
# Load state.json for context
jq '.elicitation, .topic, .topic_slug' "$REPORTS_DIR/state.json"
Build the working set based on SCOPE:
all→jq '.findings' "$REPORTS_DIR/state.json"dimension:{dim}→jq --arg d "{dim}" '[.findings[] | select(.dimension == $d)]' "$REPORTS_DIR/state.json"finding:{id}→jq --arg id "{id}" '[.findings[] | select(.id == $id)]' "$REPORTS_DIR/state.json"
If working set size exceeds CLAIM_BUDGET, fail loudly: report the count, request budget increase, and STOP. Do NOT silently truncate.
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 · 251 lines · 263 tokens per session scan A 567491869903
falsification-analyst is an agent published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 15d ago), licensed MIT. It adds 263 tokens to every session and 2,785 once invoked, about $0.0013 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}}.