agent-taskupdate

A command that reads the project's task files and reports what is in progress, what was recently done, and what should happen next.

In plain words
What is it for?
Use it to review STATE.md, PROGRESS.md, and BACKLOG.md, assess blockers, and update the project's current state.
Why use it?
It gives the agent a current view of unfinished work instead of relying on memory from an earlier session.

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/gpt-cmdr/ras-commander/agent-taskupdate
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

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 800 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 $0.00800
Opus 5 $0.00000 $0.00400
Sonnet 5 $0.00000 $0.00160
Haiku 4.5 $0.00000 $0.00080

Measured 2d ago against content hash e36742aedd1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-taskupdate 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.

.claude/commands/agent-taskupdate.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Look at your task list and memory, assess your current progress, and make a detailed plan to continue making progress on your task list.

Task Update Protocol

1. Read Current State (Do This First)

Read the following files to understand the current situation:

agent_tasks/.agent/STATE.md      -- Current project state, what's in progress
agent_tasks/.agent/PROGRESS.md   -- Recent session history (last 2-3 entries)
agent_tasks/.agent/BACKLOG.md    -- All tasks and their status

If these files don't exist, look for task planning documents in agent_tasks/ root or agent_tasks/tasks/.

2. Assess Current Progress

For the currently in-progress task:

  • What was accomplished in the last session?
  • Are there blockers?
  • What is the next concrete action?

For the backlog:

  • Are any "Blocked" tasks now unblocked?
  • Have new tasks emerged from the current work?

3. Update STATE.md

Update agent_tasks/.agent/STATE.md with:

  • Current timestamp
  • What is currently in progress
  • Health status (Green / Yellow / Red)
  • Any blockers discovered
  • Next priorities

STATE.md format:

# Project State

**Last Updated**: {YYYY-MM-DD HH:MM}
**Session**: {N}
**Health**: Green | Yellow | Red

## Current Focus
{What task is actively being worked on}

## Next Priorities
1. {Priority 1}
2. {Priority 2}

## Blockers
- {Any blockers, or "None"}

## Recent Accomplishments
- {What was done recently}

4. Append to PROGRESS.md

Append a new session entry to agent_tasks/.agent/PROGRESS.md:

## Session {N} — {YYYY-MM-DD}

### Accomplished
- {What was done}

### Decisions Made
- {Any key decisions and rationale}

### Files Modified
- {List of files}

### Handoff Notes
{Context the next session needs to know immediately}

### Next Session Should Start With
1. {First action}
2. {Second action}

PROGRESS.md is append-only — never edit previous entries.

5. Update BACKLOG.md

Update task status:

  • Mark completed tasks with [x]
  • Add any new tasks discovered
  • Move newly-unblocked tasks from Blocked to Ready
  • Add notes to tasks based on current findings

Read the full file on GitHub · 130 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 · 130 lines · 0 tokens per session scan A e36742aedd1a

Subscribe to this mod's changes

agent-taskupdate is a command published in the GitHub repository gpt-cmdr/ras-commander (78 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 800 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.