update-tasks

A command for updating task files and progress dashboards stored under docs/tasks and docs/issues. It can mark tasks complete, start them, block them with a reason, or regenerate a dashboard.

In plain words
What is it for?
Use it to start, complete, or block individual tasks and to rebuild the progress dashboard for an issue.
Why use it?
It keeps task checkboxes, issue progress, and dashboard information aligned without editing each tracking file manually.

Command for Claude Code

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/agentsea/flashbacker/update-tasks
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,074 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 $0.00000 $0.02074
Opus 5 $0.00000 $0.01037
Sonnet 5 $0.00000 $0.00415
Haiku 4.5 $0.00000 $0.00207

Measured 2d ago against content hash c88048d2ef3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-tasks 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.

templates/.claude/commands/fb/update-tasks.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Task Progress and Completion

Mark tasks as complete, update progress tracking, and maintain task dashboards.

Directory Structure

docs/tasks/                     # Task files location (read/write here)
├── ISSUE-XXX-name/             # Per-issue task directories
│   ├── README.md               # Task progress dashboard (update this)
│   ├── phase-1-name.md         # Phase task files (update checkboxes here)
│   ├── phase-2-name.md         # Additional phase files
│   └── phase-N-name.md         # All phase files for completion tracking

docs/issues/                    # Issue files location (reference only)
├── ISSUE-XXX-title.md          # Parent issue files
└── README.md                   # Issue tracking (may update status here)

Usage

/fb:update-tasks <issue-number> <action> [task-id] [notes]

Examples:

  • /fb:update-tasks ISSUE-027 complete 1.1.1 - Mark task 1.1.1 as complete
  • /fb:update-tasks ISSUE-027 start 2.1.1 - Mark task as started/in-progress
  • /fb:update-tasks ISSUE-027 block 1.3.2 waiting for security review - Block task with reason
  • /fb:update-tasks ISSUE-027 dashboard - Regenerate progress dashboard
  • /fb:update-tasks ISSUE-027 complete 1.1.2 implemented template signer - Complete with notes

Command Implementation

Parse the command arguments:

  • Argument 1 (required): Issue number (ISSUE-027, ISSUE-015, etc.)
  • Argument 2 (required): Action (complete, start, block, dashboard, progress)
  • Argument 3 (conditional): Task ID for complete/start/block actions (1.1.1, 2.3.4, etc.)
  • Argument 4+ (optional): Notes or reason text (remaining arguments joined as text)

Argument Parsing Logic

  1. Extract Issue Number: First argument must match ISSUE-XXX pattern
  2. Extract Action: Second argument determines operation type
  3. Extract Task ID: Third argument for actions requiring specific task
  4. Extract Notes/Reason: Remaining arguments joined as notes or block reason
  5. Validate Inputs: Ensure issue exists and task ID is valid format

Read the full file on GitHub · 206 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. 2d ago First seen · 206 lines · 0 tokens per session scan A c88048d2ef3a

Subscribe to this mod's changes

update-tasks is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,074 tokens. 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.