agent-taskclose

A task-closing command that records what was completed, learned, changed, or left unresolved before ending the conversation.

In plain words
What is it for?
Use it to write task findings, preserve useful patterns or workflow notes, and document changed files and remaining blockers.
Why use it?
It reduces the risk of losing important project context when the session ends.

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-taskclose
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 957 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 $0.00957
Opus 5 $0.00000 $0.00478
Sonnet 5 $0.00000 $0.00191
Haiku 4.5 $0.00000 $0.00096

Measured 2d ago against content hash 1c8c0d02d067, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-taskclose 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-taskclose.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

End the conversation after this message. Ultrathink and use your remaining output to perform comprehensive task closeout.

CRITICAL: You have maximum context RIGHT NOW about this task's working files, findings, and learnings. This context will be lost after this session. Extract and consolidate aggressively.

1. Knowledge Extraction (Do This First)

While you still have full context, extract valuable knowledge to persistent locations:

Write Task Findings

Write a consolidated markdown file that captures:

  • What was accomplished
  • Key findings and decisions made
  • Patterns discovered that could benefit future work
  • Blockers encountered and how they were resolved (or remain unresolved)
  • References to files created/modified

Location: .claude/outputs/{relevant-subagent}/ or agent_tasks/.agent/PROGRESS.md

Identify Knowledge Placement Opportunities

Ask yourself: Does any knowledge from this task belong in the permanent hierarchy?

Knowledge Type Placement Location
Coding pattern discovered .claude/rules/{category}/
Workflow learned .claude/skills/{skill}/ or update existing
Domain insight (HEC-RAS) ras_commander/{subpackage}/AGENTS.md
Shared best practice nearest relevant AGENTS.md
Claude-only best practice .claude/rules/
Troubleshooting solution relevant AGENTS.md or Claude-only rule file

Action: If significant, write/update the appropriate file. If minor, note it in your closeout findings for later review.

Update Multi-Session State (if applicable)

If this task spans sessions via agent_tasks/:

  • Update STATE.md with current snapshot
  • Append to PROGRESS.md with session summary
  • Update BACKLOG.md with completed/new items

2. Pre-Consolidation

You know which outputs are related - consolidate them now rather than leaving scattered files for later cleanup:

Merge Related Outputs

If you created multiple small outputs during this task:

  • Consolidate into single summary document
  • Move originals to .old/ with note "consolidated into {summary-file}"

Read the full file on GitHub · 129 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 · 129 lines · 0 tokens per session scan A 1c8c0d02d067

Subscribe to this mod's changes

agent-taskclose is a command published in the GitHub repository gpt-cmdr/ras-commander (78 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 957 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.