init

A command that loads or reloads research context for Sigint, a project for organizing research reports. It can load the current session, one topic, or all topics, and creates and checks the project configuration when needed.

In plain words
What is it for?
Use it to initialize a research project, reload one topic from its report folder, or load the complete research history. It also applies the project's configuration rules and validates the configuration file.
Why use it?
It restores the background information an agent needs when starting work or switching topics. Loading only the relevant reports can reduce unnecessary context, while loading everything preserves the full project history.

Command

Install

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.

agentmods
npx agentmods add commands/zircote-plugins/sigint/init
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/sigint
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00691
Opus 5 $0.00005 $0.00345
Sonnet 5 $0.00002 $0.00138
Haiku 4.5 $0.00001 $0.00069

Measured 2d ago against content hash 7bc9047773b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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.

commands/init.md · 89 lines

What it actually says

Manually initialize the research context for sigint.

Arguments:

  • --full - Load all sigint-related context (not just current session)
  • --topic - Load context for a specific topic

Process:

  1. If --topic specified: Load only context related to that topic from ./reports/[topic_slug]/.

  2. If --full specified: Load comprehensive sigint context from all topics. May use more context window but provides full history.

  3. Load configuration (Config Resolution Protocol):

    Apply the Config Resolution Protocol:

    1. Read protocols/CONFIG-RESOLUTION.md and follow all steps.
    2. Apply with topic_slug = null (init operates at project level, not topic level).
    3. Result: config and project_config are now available.

    If ./sigint.config.json does not exist, create it using jq (per Structured Data Protocol):

    jq -n '{
      version: "2.0",
      defaults: {
        report_format: "markdown",
        audiences: ["technical"]
      },
      research: {
        maxDimensions: 5,
        dimensionTimeout: 300,
        defaultPriorities: ["competitive", "sizing", "trends"]
      },
      topics: {}
    }' > ./sigint.config.json
    jq -e -f schemas/sigint-config.jq ./sigint.config.json > /dev/null
    

    Legacy config detection: After config resolution, check for ./.sigint.config.json (v1.0). If found, display:

    Legacy config detected: {found file(s)}
    Run /sigint:migrate to convert to sigint.config.json v2.0 and preserve all settings.
    

    Continue initialization regardless.

  4. Display loaded context:

    Research Context Loaded
    ───────────────────────
    Research Sessions: [count]
    Active Session: [topic or "none"]
    
    Configuration (sigint.config.json v2.0):
    - Default Repo: [config.default_repo or "not set"]
    - Report Format: [config.report_format]
    - Audiences: [config.audiences]
    - Topics configured: [count of keys in project_config.topics, or 0]
    
  5. Suggest next action:

    • If active session: suggest /sigint:status
    • If no session: suggest /sigint:start <topic>
    • If stale session: suggest /sigint:update

Note: This command supplements the SessionStart hook which provides basic awareness. Use this command to manually reload full research context mid-session or after configuration changes.

Output:

  • Confirmation of context loaded
  • Configuration status
  • Suggested next action

Example usage:

/sigint:init
/sigint:init --full
/sigint:init --topic "AI assistants"
Changes

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.

  1. 2d ago First seen · 89 lines · 0 tokens per session scan A 7bc9047773b7

Subscribe to this mod's changes

init is a command published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 15d ago), licensed MIT. It adds 10 tokens to every session and 691 once invoked, about $0.0001 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.

Related

Other commands, from other repositories

radar-council

The on-demand strategic war room. Spins up a REAL experimental agent team of 4 analyst teammates (pricing, product gap, threat and sentiment, devil's advocate) over the latest briefing. They message and challenge each other like a scientific debate, converge on recommended moves, and the addendum is published to all…

sabahudin-web/competitive-intelligence-radar · 73 tokens

radar

The weekly competitor gather run. Fans out one competitor-scout subagent per competitor in parallel, each returning a cited dossier via BrightData, then diffs against last week, merges one briefing, and publishes to all three surfaces (local folder, Notion, HTML dashboard). Runs autonomously. Run /radar-setup first.

sabahudin-web/competitive-intelligence-radar · 67 tokens

radar-setup

One-time setup for Competitive Intelligence Radar. Asks about your BrightData and Notion connection and live-tests both, then shows the proposed Notion schema for your approval before creating anything, then checks the agent-teams prerequisites for the council. Run this before /radar.

sabahudin-web/competitive-intelligence-radar · 55 tokens

build-market-research

Build comprehensive market research with industry analysis, future trends, and strategic opportunities.

armoin2018/ai-ley · 14 tokens

agent-improve

Review this conversation and generate a structured improvement report.

metabase/metabase · 0 tokens

uxbot-aggregate

Aggregate per-task UXBot reports into an overall UX report, looking for patterns across tasks.

metabase/metabase · 0 tokens