task-done

task-done is a command for Claude Code from furkantokkan/agent-foundry. It costs 21 tokens per session (349 once invoked), scanned A, original, MIT.

A task-closing workflow for marking a completed implementation or defect fix as ready to close. It checks that required evidence is current and that no defects remain unresolved.

In plain words
What is it for?
Use it to close a production task after its work and verification are complete, or to mark an obsolete task as replaced by a validated one.
Why use it?
It prevents tasks from being closed using missing, contradictory, or outdated proof.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Good fit Use it to close a production task after its work and verification are complete, or to mark an obsolete task as replaced by a validated one.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/furkantokkan/agent-foundry/task-done
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.

Clone the repo
git clone --depth 1 https://github.com/furkantokkan/agent-foundry

Made for: Claude Code.

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 task-done

README.md
[![agentmods](https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-done/github.svg)](https://agentmods.dev/commands/furkantokkan/agent-foundry/task-done)
Your own site
<a href="https://agentmods.dev/commands/furkantokkan/agent-foundry/task-done"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-done/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for task-done

Your own site · 80×15
<a href="https://agentmods.dev/commands/furkantokkan/agent-foundry/task-done"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-done.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00021 $0.00349
Opus 5.5 $0.00008 $0.00140
Sonnet 5.5 $0.00004 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 5d ago against content hash 12c01c7343fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-29, from the pricing page.

Security

Grade A, and why

task-done 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 5d 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/task-done.md · 31 lines

What it actually says

Task Done

Use the task-done Codex skill for this request.

Resolve a complete ID only to production/tasks/<ID>/contract.md. Require fresh READY_TO_CLOSE evidence, zero unresolved or blocked defect-ledger rows, and fresh VERIFIED evidence for every known defect. The close-ready state may come from a clean direct implementation with an empty ledger or from task-cycle; do not require a defect cycle when no defect exists. Refuse contradictory or stale lifecycle state. Under the shared lifecycle lock, recompute the canonical reviewed/evidence identities without rerunning tests. Preserve the defect ledger while updating only the managed lifecycle block, and do not ask for a second close confirmation. Never run implementation/tests, mutate Unity, commit, or push. A later same-scope defect enters through /task-bug <ID> "<feedback>"; its downstream cycle reopens the same task and defect record safely.

For validated orphan reconciliation, --superseded-by <NEW-ID> closes the old planning task with Closure mode: superseded only after proving the ready replacement links back to it and the old task has no active owner or progress. Preserve all evidence and return STALE_TASK_RECONCILIATION_REQUIRED on any conflict; never delete the old task.

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. 5d ago First seen · 31 lines · 21 tokens per session scan A 12c01c7343fb

Subscribe to this mod's changes

task-done is a command published in the GitHub repository furkantokkan/agent-foundry (10 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 349 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-25.