SKILLEMALL.ai
GitHub ↗ RU Sign in

AB codeflow

Codeflow streams coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) to Discord or Telegram in real-time. Use when invoking coding agents and wanting transparent, observable dev sessions — no black box. Parses Claude Code's stream-json output into clean formatted messages showing tool calls, file writes, bash commands, and results with zero AI token burn. Use when asked to "stream to Discord", "stream to Telegram", "relay agent output", or "make dev sessions visible".

ClawHub Agent Skills author: subjadeites v2.0.2 MIT-0 53 files · 8 scripts body ≈ 3 805 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice

IntegrationDiscordTelegramSoftware developmentAI 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
A
91/100
safety, quality, tests
Safety 60%
87
Quality 40%
96
Run on models
none yet
Process rating
B
67/100
Nearly there
When it triggers w 12
20
Inputs and preconditions w 11
30
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.

Secrets in code 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • medium Secrets in code secret-private-key scripts/_internal/py/redaction.py:53
      Private key material (detector / deny-list definition; key header without key body)
      "-----BEGIN PRIVATE KEY----- …", out
      detectorheader only
    • low Exfiltration exfil-webhook-url references/setup.md:54
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      echo "https://discord.com/api/webhooks/<ID>/<TOKEN>" > {baseDir}/scripts/.webhook-url
      placeholder
    • low Exfiltration exfil-webhook-url scripts/_internal/bin/dev-relay.sh:475
      Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)
      echo "  Create it: echo 'https://discord.com/api/webhooks/ID/TOKEN' > $ROOT_DIR/.webhook-url" >&2
      vendor-hostquoted
    • low Exfiltration exfil-webhook-url scripts/_internal/bin/dev-relay.sh:562
      Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)
      url = f"https://api.telegram.org/bot{tok}/getMe"
      vendor-hostquoted
    • low Exfiltration exfil-webhook-url scripts/_internal/bin/parallel-tasks.sh:168
      Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)
      echo "  Create it: echo 'https://discord.com/api/webhooks/ID/TOKEN' > $ROOT_DIR/.webhook-url" >&2
      vendor-hostquoted
    • low Exfiltration exfil-webhook-url scripts/_internal/bin/test-smoke.sh:133
      Webhook / callback URL commonly used for exfiltration (verify the destination) (test fixture / example file; the skill's own vendor host; quoted — discussed, not commanded)
      url = f"https://api.telegram.org/bot{tok}/getMe"
      fixturevendor-hostquoted
    • low Exfiltration exfil-webhook-url scripts/_internal/py/platforms/telegram.py:140
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      url = f"https://api.telegram.org/bot{BOT_TOKEN}/{method}"
      placeholder
    • low Exfiltration exfil-webhook-url scripts/_internal/py/platforms/telegram.py:196
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      url = f"https://api.telegram.org/bot{BOT_TOKEN}/{method}"
      placeholder
    • low Secrets in code secret-github-token scripts/_internal/py/tests/test_parse_stream_output_mode_and_state_window.py:86
      GitHub token (placeholder value)
      secret = "ghp_…789"
      placeholder

    Files scanned: 53. 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 67/100

    • 20When it triggers. No condition that starts the skill
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 16 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 103 steps
    • 100Failures and branches. 12 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3805 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (10 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 481: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 103 items
    • +3Output format is stated explicitly
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: suspicious
    This appears to be a real session-streaming tool, but it also weakens agent permission controls and can change OpenClaw plugin/gateway settings, so it needs review before installation.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026