SKILLEMALL.ai
GitHub ↗ RU Sign in

BB durable-task-runner

Run long-running, multi-step work in OpenClaw without losing it to resets: durable state, progress updates, smart 'continue this' recovery, verification before completion, and optional worker-lane coordination for larger jobs. Use when work spans multiple phases, must survive agent or gateway resets, or should not depend on ad-hoc chat memory. Best fit for users who want explicit recovery after interruption rather than fragile background scheduler setup.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: wonko6x9 v0.1.6 MIT-0 77 files · 3 scripts body ≈ 1 240 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
71
Quality 40%
81
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

  • high Dangerous commands cmd-persistence scripts/task_install_tick_cron.sh:50
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    } | sed '/^$/N;/^\n$/D' | crontab -
Medium and low: 3
  • medium Dangerous commands cmd-privilege README.md:67
    Privilege escalation / world-writable permissions
    - no privilege-escalation logic (`sudo`, setuid/capability manipulation, service-install tricks)
  • medium Dangerous commands cmd-persistence scripts/task_install_tick_cron.sh:45
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    current="$(crontab -l 2>/dev/null || true)"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/task_install_tick_cron.sh:45
    Mentions editing / listing crontab (string literal in code, not executed)
    current="$(crontab -l 2>/dev/null || true)"
    code literal

Files scanned: 46. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 65/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 60 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1240 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (3 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -317 of 28 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 458: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 60 items
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: suspicious
This skill is mostly coherent for durable task tracking, but it needs review because it can bind active chat/session metadata, send task status externally, install recurring ticks, and delete a user-supplied install target.
LLM: suspicious (high) · VirusTotal: · 29 May 2026