agentmods.dev

task-orphan-check

task-orphan-check is a skill for Claude Code from sonichi/sutando. It costs 65 tokens per session (10,802 once invoked), scanned A, original, MIT.

A recovery check for tasks left in a tasks folder after an earlier agent run stopped unexpectedly. It compares task files with records of actions already taken before deciding whether to finish, recover, or archive them.

In plain words
What is it for?
Use it at startup or manually to classify and recover abandoned tasks, especially tasks involving sent messages, written result files, or archived work.
Why use it?
It helps prevent an unfinished task from being run twice after an agent crash, which could send duplicate messages or repeat other side effects.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is WS="$(bash scripts/sutando-config.sh workspace)".

not rated 404repo +3 changed 2d ago A scan SkillSpector: pass 65 tokens original MIT

Good fit Use it at startup or manually to classify and recover abandoned tasks, especially tasks involving sent messages, written result files, or archived work.

Compare 6 skills from other repositories ↓
View source ↗ sonichi/sutando sutando.ai
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando
agentmods
npx agentmods add skills/sonichi/sutando/task-orphan-check

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-orphan-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/task-orphan-check/github.svg)](https://agentmods.dev/skills/sonichi/sutando/task-orphan-check)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/task-orphan-check"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/task-orphan-check/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-orphan-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/sonichi/sutando/task-orphan-check"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/task-orphan-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,802 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00065 $0.10802
Opus 5.5 $0.00026 $0.04321
Sonnet 5.5 $0.00013 $0.02160
Haiku 4.5 $0.00006 $0.01080

Measured 2d ago against content hash ea9ffe577699, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-orphan-check 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/classify.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/task-orphan-check/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task orphan check

Recovery half of the post-#1049 task-bridge redesign. Replaces the brittle attempts-counter (#1049 + #1066's followup) with a startup-time classification pass that uses existing side-effect markers (PR #1048's .sending files for Discord, result files in results/, archive presence) to decide what to do with each live task in <workspace>/tasks/.

Usage: /task-orphan-check

Designed to be invoked from /startup (PR #1072) as step 1, before /schedule-crons starts the task watcher. Also callable standalone for manual recovery.

Why this exists

If the agent crashes mid-task with non-idempotent side effects already executed (Discord message sent, file written, API call made) but the archive of result + task files never ran, on restart the task file is still in tasks/. The watcher re-emits it. The agent re-processes. The side effect fires a second time.

PR #1049 tried to solve this with an attempts: N counter inside the task file — but the bumper-write fired the watcher's own Renamed event, creating an infinite self-trigger loop. PR #1066 tried to patch the loop by switching to in-place writes — but on macOS, open(file, 'w') STILL fires the Created event because O_WRONLY|O_CREAT|O_TRUNC flips the ItemCreated bit. Both PRs are working around the wrong layer.

This skill moves the dedup logic out of the watcher's event surface entirely. The agent does a single classification pass at startup, cross-references markers that already exist (PR #1048 ships them for Discord delivery; result files in results/ mark "this task was completed"), and decides per-task what to do. No counter, no in-band writes, no self-trigger loop.

On Activation

The procedure below is non-LLM where possible — mechanical file checks + side-effect marker reads. The LLM-judgment parts are bounded (per-task classification with explicit decision rules).

Step 1 — List live tasks

WS="$(bash scripts/sutando-config.sh workspace)"
ls "$WS/tasks/"task-*.txt 2>/dev/null | head -200

Read the full file on GitHub · 277 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed · +3 lines ea9ffe577699
  2. 6d ago Changed · +1 lines ad3272ae6b64
  3. 1mo ago Changed · +10 lines 80b33357d931
  4. 1mo ago Changed · +27 lines 682bce251552
  5. 2mo ago First seen · 236 lines · 65 tokens per session scan A a278733e477d

Subscribe to this mod's changes

task-orphan-check is a skill published in the GitHub repository sonichi/sutando (404 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 10,802 once invoked, about $0.0003 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 2026-08-30.

ai-agentclaudegeminimacosopen-sourcepersonal-ai
Related

task-orphan-check compared with skills from other repositories

task-orphan-check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
task-orphan-checksonichi/sutandoSkill404yesterdayMITA65Claude Code
app-buildervellum-ai/vellum-assistantSkill1.5k2d agoMITA162Claude Code, Codex
gmailvellum-ai/vellum-assistantSkill1.5k2d agoMITA20Claude Code, Codex
guardian-verify-setupvellum-ai/vellum-assistantSkill1.5k2d agoMITA26Claude Code, Codex
stripe-link-walletvellum-ai/vellum-assistantSkill1.5k2d agoMITA52Claude Code, Codex
assistant-migrationvellum-ai/vellum-assistantSkill1.5k2d agoMITA90Claude Code, Codex
vellum-memory-v2-migrationvellum-ai/vellum-assistantSkill1.5k2d agoMITA34Claude Code, Codex