SKILLEMALL.ai
GitHub ↗ RU Sign in

CC session-tracker

MUST be invoked before any multi-step task where crash-resilient recovery is desired — without `init`, a session drop loses mid-task state unrecoverably. Discloses: writes persistent JSON state to .session/ (task name, step list, file paths declared by agent, worklog entries — no file contents; FS scanning OFF by default); parses TodoWrite JSON from stdin via `sync`; optional detached background monitor (opt-in via `monitor --start`, 24h-bounded, foreground alternative available, output logged to .session/monitor.log). No network, no eval, no env harvesting, no file content reading. Includes `cleanup` (irreversible, requires --force or confirmation) and `prune` (auto-remove sessions older than 7 days). Ships as SKILL.md + scripts/session_tracker.py (Python stdlib only).

ClawHub Agent Skills author: DarkD v2.3.0 MIT-0 3 files body ≈ 6 394 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorAI and agentsInfrastructurePersonal productivitytype 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
C
73/100
safety, quality, tests
Safety 60%
85
Quality 40%
56
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-privilege SKILL.md:100
    Privilege escalation / world-writable permissions
    sudo tee /usr/local/bin/session-tracker <<'EOF'
  • medium Dangerous commands cmd-privilege SKILL.md:104
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/session-tracker
  • medium Dangerous commands cmd-privilege SKILL.md:462
    Privilege escalation / world-writable permissions
    sudo rm -f /usr/local/bin/session-tracker   # if wrapper installed

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6394 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 60/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 29 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 6394 tokens
  • 100Steps. 52 steps
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill

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
  • -5TODO / placeholder text left in the skill
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +3Description length 780: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 52 items
  • +4Has examples (26 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.

External checks

ClawHub: clean
This skill is a local crash-recovery helper that persistently records task progress and optional filesystem metadata, with its main behaviors disclosed and aligned with its purpose.
LLM: benign (high) · VirusTotal: · 25 Jul 2026