Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add atman-33/workhub --skill opencode-log-investigationgit clone --depth 1 https://github.com/atman-33/workhubWrote 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.
[](https://agentmods.dev/skills/atman-33/workhub/opencode-log-investigation)<a href="https://agentmods.dev/skills/atman-33/workhub/opencode-log-investigation"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/opencode-log-investigation/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.
<a href="https://agentmods.dev/skills/atman-33/workhub/opencode-log-investigation"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/opencode-log-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00508 |
| Opus 5 | $0.00023 | $0.00254 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
opencode-log-investigation 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 7d ago.
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.
What it actually says
OpenCode Log Investigation
Quick start
- Identify the latest log file:
- Windows:
%USERPROFILE%\.local\share\opencode\log\ - Linux/macOS:
~/.local/share/opencode/log/
- Windows:
- Open the most recent
YYYY-MM-DDTHHMMSS.log. - Search for
ERRORlines to find the root cause.
Workflows
1. Plugin loading issues
- Search for
service=pluginin the log. - Check if the target plugin appears as
loading plugin. - If absent, verify
opencode.jsonhas the plugin in thepluginarray. - If present but errors follow, inspect the stack trace immediately after the load line.
2. MCP server failures
- Search for
service=mcpandERROR. - Common errors:
MCP error -32000: Connection closed→ the command failed to start.The system cannot find the path specified→ the executable (e.g.,/bin/bash,uvx) is missing or not in PATH.
- Check the
command=field in the error line to see the exact command invoked.
3. Session or tool errors
- Search for
service=sessionorservice=tool.registry. - Look for
error=orfailedin the same block. - Cross-reference timestamps to match user-visible terminal errors with log entries.
4. Shell command errors inside plugins
- If a plugin uses
ctx.$to run shell commands,console.erroroutput from the plugin may not appear in the OpenCode log. - Check the terminal output directly, or redirect plugin stderr to a temp file for debugging.
- Verify the command exists in the OS PATH (e.g.,
python3vspythonon Windows).
Advanced features
- See REFERENCE.md for a detailed error pattern catalog.
- For plugin-specific debugging, add
console.login the plugin and watch the terminal; OpenCode does not capture plugin stdout/stderr into its log file.
What ships with it
1 file 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.
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.
- 7d ago First seen · 49 lines · 46 tokens per session scan A 114ca53f9d6b
opencode-log-investigation is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 508 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-fix
A bug-fixing skill with separate paths for directly reported bugs, correctness-review findings, and failed verification or quality-gate reports. It records completed fixes and their validation in project reports.
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…