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 hamakyo/okf-skills --skill investigate-buggit clone --depth 1 https://github.com/hamakyo/okf-skillsWrote 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/hamakyo/okf-skills/investigate-bug)<a href="https://agentmods.dev/skills/hamakyo/okf-skills/investigate-bug"><img src="https://agentmods.dev/badge/skills/hamakyo/okf-skills/investigate-bug/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/hamakyo/okf-skills/investigate-bug"><img src="https://agentmods.dev/badge/skills/hamakyo/okf-skills/investigate-bug.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 | $0.00045 | $0.00569 |
| Opus 5.5 | $0.00018 | $0.00228 |
| Sonnet 5.5 | $0.00009 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
investigate-bug 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Bug
When to use
Use this Skill when:
- A failure needs reproduction.
- The root cause is unknown.
- A regression or incident may affect multiple areas.
- The user asks for diagnosis, triage, or investigation.
Do not use this Skill when:
- The task is a straightforward implementation request.
- The exact fix is already known and only needs to be applied.
- The work is only adding test coverage for known behavior.
Inputs
- Bug report, failing command, stack trace, screenshot, or reproduction notes.
- Expected behavior and actual behavior.
- Environment details if available.
- Relevant OKF documents if the behavior is domain-specific.
Required context
Before editing code, read:
README.mdAGENTS.mdorCLAUDE.md, depending on the tool in useokf/index.mdand relevant OKF documents when the bug relates to documented behavior- Existing tests for the affected area
- Recent changes or
git diffwhen the bug may be introduced locally
Workflow
- Capture the reported symptom.
- Identify or create the smallest reproduction path.
- Run the failing test, command, or scenario when possible.
- Compare actual behavior with documented or expected behavior.
- List plausible root causes with evidence.
- Inspect the narrowest relevant code paths.
- Determine impact scope and whether related behavior may also be affected.
- Propose the smallest fix and the test that should prevent recurrence.
- Only implement the fix if the user requested implementation or the task clearly expects it.
Guardrails
- Do not jump directly to a fix before reproduction or evidence.
- Do not rewrite broad areas while investigating.
- Do not ignore OKF if it defines the expected behavior.
- Do not treat speculation as confirmed root cause.
- Do not remove failing tests to make the suite pass.
- Do not add secrets, credentials, private URLs, or personal data to logs or docs.
Completion checklist
- Symptom is described.
- Reproduction was attempted and result is documented.
- Expected behavior source is identified or uncertainty is stated.
- Root cause candidates are ranked by evidence.
- Impact scope is summarized.
- Minimal fix and test plan are proposed or implemented.
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.
- 1mo ago First seen · 80 lines · 45 tokens per session scan A 67ee1937e2c3
investigate-bug is a skill published in the GitHub repository hamakyo/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.
debug
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
five-whys
Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why something keeps happening, or wants the root cause rather than a quick fix.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.