SKILLEMALL.ai
GitHub ↗ RU Sign in

DC opencode-qa

QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event stream, smoke-test the TUI under tmux, and investigate sessions in opencode's SQLite DB by id, title/name, or message text. Ships tested helper scripts (each with a --self-test) plus per-domain references. Use whenever someone wants to QA, smoke-test, verify, or debug opencode's CLI, HTTP server, plugin hooks/events, or TUI, or to find/inspect opencode sessions in the database. Triggers: opencode qa, qa opencode, test opencode, verify opencode hook, opencode session db, find opencode session by id/name/text, opencode tui test, opencode server health, opencode event stream.

code-yeongyu/oh-my-openagent Agent Skills author: code-yeongyu NOASSERTION 22 files · 13 scripts body ≈ 2 691 tokens Open the sourcegithub.com↗ analyzed 4 h ago

QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event…

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationDockerSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
59/100
safety, quality, tests
Safety 60%
43
Quality 40%
83
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 21

    ✓ No critical or high findings

    Medium and low: 21
    • medium Exfiltration net-credential-use references/events-hooks.md:23
      Credential used in a network call (verify the destination is the intended service)
      curl -N -u opencode:$PASS "http://127.0.0.1:4096/event?directory=$PWD"
    • medium Exfiltration net-credential-use references/events-hooks.md:69
      Credential used in a network call (verify the destination is the intended service)
      curl -N -u opencode:$PASS "http://127.0.0.1:4096/event?directory=$PWD" \
    • medium Exfiltration net-credential-use references/events-hooks.md:73
      Credential used in a network call (verify the destination is the intended service)
      curl -X POST -u opencode:$PASS -H 'Content-Type: application/json' \
    • medium Exfiltration net-credential-use references/server-api.md:60
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u opencode:$PASS http://127.0.0.1:4096/doc | jq '.paths | keys'
    • medium Exfiltration net-credential-use references/server-api.md:68
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u opencode:$PASS http://127.0.0.1:4096/global/health | jq .
    • medium Exfiltration net-credential-use references/server-api.md:71
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u opencode:$PASS http://127.0.0.1:4096/doc | jq '.paths|length'
    • medium Exfiltration net-credential-use references/server-api.md:77
      Credential used in a network call (verify the destination is the intended service)
      curl -s -u opencode:$PASS "http://127.0.0.1:4096/session?directory=$PWD" | jq 'length'
    • medium Exfiltration net-credential-use references/server-api.md:191
      Credential used in a network call (verify the destination is the intended service)
      curl -X POST -u opencode:$PASS -H 'Content-Type: application/json' \
    • medium Exfiltration net-credential-use SKILL.md:107
      Credential used in a network call (verify the destination is the intended service)
      curl -X POST -u opencode:$OPENCODE_SERVER_PASSWORD -H 'Content-Type: application/json' \
    • low Secrets in code secret-high-entropy-token scripts/db-session-by-id.sh:6
      High-entropy token-like string (may be an id, hash or a credential)
      #   db-session-by-id.sh ses_…Eb3
    • low Secrets in code secret-high-entropy-token scripts/export-roundtrip.sh:10
      High-entropy token-like string (may be an id, hash or a credential)
      #   export-roundtrip.sh ses_…PjZ   # prints clean JSON
    • low Dangerous commands cmd-background-process scripts/lib/common.sh:139
      Starts a background / autostarted process
      disown "$OQA_SERVER_PID" 2>/dev/null || true
    • low Dangerous commands cmd-background-process scripts/serve-wake-split-probe.sh:119
      Starts a background / autostarted process
      disown "$FAKE_SERVER_PID" 2>/dev/null || true
    • low Exfiltration net-credential-use scripts/serve-wake-split-probe.sh:312
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      status_json="$(curl -sf -u "opencode:${pass}" "${url}/session/status" 2>/dev/null)" || true
      quoted
    • low Exfiltration net-credential-use scripts/serve-wake-split-probe.sh:563
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      health_code="$(curl -so /dev/null -w "%{http_code}" -u "opencode:${OQA_SERVER_PASS}" \
      quoted
    • low Dangerous commands cmd-background-process scripts/serve-wake-split-probe.sh:779
      Starts a background / autostarted process
      disown "$OQA_SERVER_PID" 2>/dev/null || true
    • low Exfiltration net-credential-use scripts/serve-wake-split-probe.sh:801
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      ses_response="$(curl -sS -u "opencode:${pass}" \
      quoted
    • low Exfiltration net-credential-use scripts/serve-wake-split-probe.sh:820
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      prompt_response="$(curl -sS -u "opencode:${pass}" \
      quoted
    • low Exfiltration net-credential-use scripts/sse-hook-probe.sh:17
      Credential used in a network call (verify the destination is the intended service) (code comment)
      #                              curl -X POST -u opencode:$PASS \
      comment
    • low Dangerous commands cmd-background-process scripts/sse-hook-probe.sh:50
      Starts a background / autostarted process
      disown "$cpid" 2>/dev/null || true
    • low Secrets in code secret-high-entropy-token SKILL.md:159
      High-entropy token-like string (may be an id, hash or a credential)
      bash scripts/db-session-by-id.sh ses_…Eb3

    Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 167): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 18 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2691 tokens
    • 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 (7 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
    • -2localhost URLs: will not work for another user
    • -31 of 9 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 734: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (8 of 8)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.