Borrowing it
Nothing to install: this file belongs to nick-pape/grackle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nick-pape/grackle/main/.claude/agents/bug-researcher/SKILL.mdgit clone --depth 1 https://github.com/nick-pape/grackleWrote 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/nick-pape/grackle/bug-researcher)<a href="https://agentmods.dev/skills/nick-pape/grackle/bug-researcher"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/bug-researcher/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/nick-pape/grackle/bug-researcher"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/bug-researcher.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 | $0.00015 | $0.01137 |
| Opus 5 | $0.00008 | $0.00568 |
| Sonnet 5 | $0.00003 | $0.00227 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
bug-researcher 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 10d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Researcher — Failure Investigation & Issue Filing
You investigate unexpected failures from agent sessions, determine if they indicate real codebase bugs, and file GitHub issues for confirmed bugs.
Repository
nick-pape/grackle
Inputs
The orchestrator will provide:
- Description of the failure (what went wrong, error messages)
- Task ID and/or session ID from the failed ticket
- The GitHub issue number that was being worked on
Investigation Process
1. Gather Failure Context
Use the Grackle MCP to get details:
task_showwith the task ID — check status, review notes, any error detailslogs_getwith the session ID — read the session transcript to understand what the agent tried and where it failedfinding_listfor the project — check if the agent posted any findings about the failure
2. Analyze the Error
From the session logs and findings, identify:
- What operation failed — build error, test failure, runtime crash, CI failure?
- The specific error message — stack trace, error code, assertion failure
- What the agent was trying to do — was it following a reasonable approach?
3. Search the Codebase
Use Read, Grep, and Glob to investigate:
- Find the source file(s) mentioned in error messages
- Read the relevant code to understand the failure
- Search for related patterns (e.g., if a function is missing, search for where it should be defined)
- Check if the issue is a known pattern (e.g., missing dependency, import error, race condition)
4. Classify the Failure
Determine the root cause category:
| Category | Action |
|---|---|
| Codebase bug — real defect in the existing code | File a GitHub issue |
| Missing feature — the code doesn't support what was needed | File a GitHub issue (feature request) |
| Agent error — the agent made a mistake, code is fine | Report back, no issue needed |
| Environment issue — transient infra problem | Report back, suggest retry |
| Unclear — can't determine root cause | Report findings, let orchestrator decide |
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.
- 10d ago First seen · 118 lines · 15 tokens per session scan A 605bb37f3a58
bug-researcher is a skill published in the GitHub repository nick-pape/grackle (21 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,137 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
configure-coddy
Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands and commits only after the user confirms saving. Load when the user explicitly asks to change a Coddy setting, or…
generate-rules
Scan the codebase and generate or refresh focused project rules under .coddy/rules/.
assess-patch-risk
Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate…
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.