agentmods.dev

fd-resume

fd-resume is a command for coding agents from DVNghiem/FlowDeck. It costs 30 tokens per session (828 once invoked), scanned A, original, MIT.

A session recovery command for restoring an interrupted FlowDeck coding session from saved checkpoint or status files.

In plain words
What is it for?
Use it to recover the current task, stage, plan, completed steps, blockers, and next action, then optionally continue without confirmation.
Why use it?
It removes the need to reconstruct manually what had already happened and what should happen next.

Command

not rated 24 16d ago A scan 30 tokens original MIT
View the source file DVNghiem/FlowDeck
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/dvnghiem/flowdeck/fd-resume
Clone the repo
git clone --depth 1 https://github.com/DVNghiem/FlowDeck

Wrote 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.

agentmods badge for fd-resume

README.md
[![agentmods](https://agentmods.dev/badge/commands/dvnghiem/flowdeck/fd-resume.svg)](https://agentmods.dev/commands/dvnghiem/flowdeck/fd-resume)
Your own site
<a href="https://agentmods.dev/commands/dvnghiem/flowdeck/fd-resume"><img src="https://agentmods.dev/badge/commands/dvnghiem/flowdeck/fd-resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 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 $0.00030 $0.00828
Opus 5 $0.00015 $0.00414
Sonnet 5 $0.00006 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 4d ago against content hash 6a1983e4382a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fd-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 4d 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.

docs/commands/fd-resume.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume

Resume a previously interrupted FlowDeck session.

Input: $ARGUMENTS — pass --yes to skip the confirmation pause.

Steps

  1. Read ~/.fd-plan/<slug>/checkpoint.json — this is the primary source.

    • If present and version is "1": rebuild the session summary from current_command, current_stage, topic, phases, worktrees, and blockers.
    • If absent, unreadable, or carrying a version this command does not understand: fall back to ~/.fd-plan/<slug>/STATE.md and log which source was used.

  2. If checkpoint.json is missing, fall back to STATE.md.

    • Read topic, status, plan_confirmed, steps_complete, last_action, next_action to reconstruct where the session stopped.
    • If STATE.md is also missing, error: "No planning workspace. Run /fd-task to start."

  3. Read STATE.md to fill in anything checkpoint.json does not carry: last_updated, plan_confirmed, steps_complete.

  4. Read ~/.fd-plan/<slug>/<topic>/plan.md if it exists — show a preview (first 20 lines).

  5. Read ~/.fd-plan/<slug>/<topic>/task.md if it exists — show the requirement count.

  6. Present the session summary:

═══════════════════════════════════════════════
RESUMING SESSION
═══════════════════════════════════════════════
Source: checkpoint.json | STATE.md (fallback)
Project: <slug>  |  Topic: <topic>
Command: <current_command> → stage: <current_stage>
Status: <status>
Phases: 1 complete, 2 in_progress, 3 pending
Last updated: <timestamp>
Plan confirmed: <yes/no>
Requirements: <X> from task.md
Worktrees: <names, or "none">
Blockers: <list, or "none">

Plan preview:
<first 10 lines of plan.md>
───────────────────────────────────────────────
Type CONFIRM to resume execution from this point.
═══════════════════════════════════════════════

  1. Unless --yes is passed, PAUSE and wait for the user to type CONFIRM.

  2. After confirmation, resume from current_command at current_stage:

    • Re-enter current_command and skip forward to current_stage — do not replay stages already recorded complete in phases.
    • If blockers is non-empty, report them and stop. Do not resume into a blocked state.
    • If worktrees is non-empty, list them and confirm whether to reuse or recreate before continuing.
    • If checkpoint.json was absent, use the STATE.md path: when plan_confirmed: true and plan.md has uncompleted steps, resume at /fd-execute; when no plan exists, start at /fd-task.
    • Brief the user on the next step before starting it.

Read the full file on GitHub · 95 lines

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. 4d ago First seen · 95 lines · 30 tokens per session scan A 6a1983e4382a

Subscribe to this mod's changes

fd-resume is a command published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 16d ago), licensed MIT. It adds 30 tokens to every session and 828 once invoked, about $0.0002 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.

Building agentsOrchestrationProductivityagentic-aiai-agentsopencodeopencode-plugin
Related

Other commands, from other repositories

md

Open a Markdown file in the browser-based annotator for review.

konradmichalik/md-annotator · 12 tokens

annotate:md

Annotate a markdown file in the browser.

konradmichalik/md-annotator · 8 tokens

switch

Switch your campy pet (cat, hamster, ghost, robot, dragon, turtle, panda, dog).

dropdevrahul/campy · 22 tokens

pet

Pet your campy pet to boost happiness.

dropdevrahul/campy · 8 tokens

play

Play with your campy pet to boost happiness.

dropdevrahul/campy · 9 tokens

campy

Show your campy pet's current status.

dropdevrahul/campy · 8 tokens