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 skills add zircote-plugins/sigint --skill falsifygit clone --depth 1 https://github.com/zircote-plugins/sigintWrote 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/skills/zircote-plugins/sigint/falsify)<a href="https://agentmods.dev/skills/zircote-plugins/sigint/falsify"><img src="https://agentmods.dev/badge/skills/zircote-plugins/sigint/falsify/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/skills/zircote-plugins/sigint/falsify"><img src="https://agentmods.dev/badge/skills/zircote-plugins/sigint/falsify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.04230 |
| Opus 5.5 | $0.00040 | $0.01692 |
| Sonnet 5.5 | $0.00020 | $0.00846 |
| Haiku 4.5 | $0.00010 | $0.00423 |
Grade A, and why
falsify 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 1mo 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sigint Falsify Skill (Adversarial Assessment + Remediation)
You are the team lead orchestrating adversarial falsification of research findings. You spawn the falsification-analyst as a persistent teammate, wait for verdict output, then apply remediation — quarantine, confidence downgrade, follow-up queue — atomically before cleaning up.
MANDATORY SWARM ORCHESTRATION
You MUST use the full swarm pattern: TeamCreate → TaskCreate → Agent(team_name) → SendMessage → TeamDelete. Do NOT spawn standalone agents.
Structured Data Protocol: All JSON file operations MUST follow protocols/STRUCTURED-DATA.md. Use jq for I/O and validate every write with the corresponding schemas/*.jq file.
One-Round Rule: A finding that already carries provenance.falsification_attempts from the current session is skipped. Do not falsify falsifications.
Phase 0: Parse Arguments and Initialize
Step 0.1: Parse Arguments
Input sanitization: truncate $ARGUMENTS to 200 characters total, strip backticks and angle brackets.
--scope→ defaultall. Valid:all,dimension:<dim>(where<dim>is one of competitive|sizing|trends|customer|tech|financial|regulatory|trend_modeling),finding:<id>(where<id>matchesf_[a-z_]+_[0-9]+). Invalid → error and stop.--query-budget→ default 6. Integer 1–10. Out of range → clamp and warn.--claim-budget→ default 50. Integer 1–500. Out of range → clamp and warn.--mode→ defaultblock. One ofblock(anyfalsifiedverdict halts downstream phases) oradvisory(all verdicts are annotation only). Invalid → error and stop.
Step 0.2: Find Active Research Session
Scan ./reports/*/state.json for sessions with status in {"active", "complete"}. Pick most recently updated. Extract topic, topic_slug, elicitation.
If no session found, error: "No research session found. Run /sigint:start <topic> first."
Resolve reports_dir from config (REQUIRED — do not hardcode paths):
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 379 lines · 100 tokens per session scan A efb713247fd4
falsify is a skill published in the GitHub repository zircote-plugins/sigint (24 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 4,230 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
gr-competitor
A competitor research workflow that collects information from rival websites, including landing pages, pricing, blogs, and past changes. Wayback refers to the Internet Archive’s record of older versions of websites.
radar-publish-council
Publishes the Strategic War Room addendum from /radar-council to all three surfaces. Appends the addendum to the local briefing markdown, fills the warroom section of the dashboard data and re-renders the dashboard, and appends the addendum to the Notion briefing page while checking its War Room box. Use after the…
executive-market-research
Generate executive-grade market research reports - full (35-45 pages) or Executive Brief (8-10 pages, quick mode) - for any product, sector or country. Triangulated sources from UN Comtrade, World Bank, IMF, EIU. Outputs PDF + interactive HTML in English, Arabic (RTL), or French. Use for market sizing (TAM/SAM/SOM)…
radar-onboard
Run this FIRST, before any other radar skill. Sets up Competitive Intelligence Radar by ASKING whether BrightData and Notion are connected, live-testing one real call to each, detecting which MCP prefix is actually live, and writing radar.config.json with the user's business context. Use when the user runs…
radar-provision-notion
Creates the two Notion databases (Competitors and Briefings) the radar publishes to, but ONLY after SHOWING the proposed schema and getting the user's explicit approval. Use during /radar-setup after onboarding, or when radar-publish-notion reports the databases are missing. Idempotent: if the databases already exist…
radar-publish-notion
Publishes the run to Notion. Upserts one row per competitor in the Competitors database (matched by domain, with a Change field for week-over-week tracking) and creates a Briefings page holding the full briefing. Use after radar-merge-briefing. Requires the databases to exist (radar-provision-notion). Writing rows to…