resume

A command for continuing a previous research session from saved progress files. It can also list available sessions and their current status.

In plain words
What is it for?
Use it to resume a named research topic, inspect its findings and progress, or list registered and older research sessions.
Why use it?
It avoids repeating research and helps an agent recover the work state before continuing.

Command

Part of the sigint plugin — 16 skills, 9 commands, 6 agents, 1 hook shipped together

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/resume
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/sigint

Or install sigint, the plugin that ships this one along with the rest of its 16 skills, 9 commands, 6 agents, 1 hook.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 836 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 $0.00008 $0.00836
Opus 5 $0.00004 $0.00418
Sonnet 5 $0.00002 $0.00167
Haiku 4.5 $0.00001 $0.00084

Measured 3d ago against content hash 4fcb58fb1c4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume 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 3d 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/resume.md · 96 lines

What it actually says

Resume a previous sigint research session following the harness initialization protocol.

Arguments:

  • $1 - Topic name to resume (optional if only one active session)
  • --list - List all available research sessions

Harness Initialization Protocol:

The resume command follows the Anthropic long-running agent harness pattern: read progress files first to understand prior work state before doing anything else.

Process:

  1. If --list specified: Read sigint.config.json topics as the primary session index (comprehension-only — Read is acceptable per Structured Data Protocol). For each topic entry with lifecycle fields (status, dimensions, created, updated, findings_count), display directly from config.

    Fall back to scanning ./reports/*/state.json for sessions not registered in the config (legacy sessions predating topic registration).

    Display table:

    | Topic | Status | Last Updated | Dimensions | Findings |
    |-------|--------|--------------|------------|----------|
    
  2. If topic specified: Load ./reports/[topic]/research-progress.md FIRST (harness init protocol). Then load ./reports/[topic]/state.json for structured data.

  3. If no topic specified: Check for single active session. If multiple, prompt user to specify. If none, suggest starting new research.

  4. Read progress file first (harness init protocol):

    Read ./reports/{topic_slug}/research-progress.md
    

    This is the human/agent-readable log of all phase transitions, codex review results, and session events. It provides the cross-session continuity that state.json alone cannot.

    If research-progress.md does not exist (legacy session), fall back to state.json only and note: "Legacy session — no progress file. Consider running /sigint:update to generate one."

  5. Restore research context (comprehension-only — Read is acceptable per Structured Data Protocol): From state.json:

    • Load all findings and sources
    • Read lineage[] to understand session history
    • Identify current research phase
    • Check for quarantined findings in ./reports/{topic_slug}/quarantine.json

    From research-progress.md:

    • Identify last completed phase
    • Note any codex review gate results
    • Check for flagged issues or gaps
  6. Display session summary:

    Research Session: [topic]
    Status: [active/paused/complete]
    Phase: [discovery/analysis/synthesis]
    Started: [date]
    Last Updated: [date]
    
    Lineage: [N] research actions
    Latest: [action] on [date] — [dimensions], [finding_count] findings
    
    Findings: [count] ([quarantined] quarantined)
    Sources: [count]
    Dimensions: [list with status]
    
    Codex Review Status:
    - Post-findings: [pass/fail/not-run]
    - Post-merge: [pass/fail/not-run]
    
    Pending Tasks:
    - [from progress file if any]
    
  7. Suggest next steps: Based on current phase, lineage, and findings:

    • If research is recent and complete → suggest /sigint:report or /sigint:issues
    • If research is stale (>30 days) → suggest /sigint:update
    • If dimensions are missing → suggest /sigint:augment <dimension>
    • If quarantined findings exist → suggest reviewing quarantine.json

Output:

  • Session summary with lineage history
  • Research state restored with progress context
  • Suggested next actions based on current state
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. 3d ago First seen · 96 lines · 8 tokens per session scan A 4fcb58fb1c4a

Subscribe to this mod's changes

resume is a command published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 16d ago), licensed MIT. It adds 8 tokens to every session and 836 once invoked, about $0.0000 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

fixbot

You are the orchestrator for the fixbot workflow. Fixbot fixes a Linear issue, running directly in this project against the locally running server. For an isolated worktree version, use /autobot /fixbot instead.

metabase/metabase · 0 tokens

reprobot

You are the orchestrator for the reprobot workflow. ReproBot attempts to reproduce a reported bug against the locally running server, classifies the result, and optionally writes a failing test. For an isolated worktree version, use /autobot /reprobot instead.

metabase/metabase · 0 tokens