Borrowing it
Nothing to install: this file belongs to nerds-odd-e/doughnut. 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/nerds-odd-e/doughnut/main/.agents/skills/dough-bug-fixing/SKILL.mdgit clone --depth 1 https://github.com/nerds-odd-e/doughnutWrote 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/nerds-odd-e/doughnut/dough-bug-fixing)<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/dough-bug-fixing"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-bug-fixing/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/nerds-odd-e/doughnut/dough-bug-fixing"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-bug-fixing.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 | $0.00107 | $0.03054 |
| Opus 5.5 | $0.00043 | $0.01222 |
| Sonnet 5.5 | $0.00021 | $0.00611 |
| Haiku 4.5 | $0.00011 | $0.00305 |
Grade A, and why
dough-bug-fixing 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 18d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve a reported discrepancy
Gather the supplied report and investigate it without repairing the product. Close any standalone exploration workspace before invoking shared execution for an authorized bounded repair. Return an evidence-backed disposition to the coordinator. Route known larger work and incomplete or inconclusive attempts as first-priority backlog stories. Do not invent a defect, dismiss a report for lack of confirmation, or treat branch delivery as integration.
Stay in request authority
A reporting-only or refinement-only request does not authorize execution or code change. Contribute the report's expectations, evidence, gaps, and acceptance examples to the existing artifact that request already owns, such as a seed under story refinement. Stop after that contribution.
Invoke this skill for an authorized discrepancy, defect, or regression, not because the instruction contains the word "fix".
Admit the accepted mission
Asking questions to understand the report is not a mission. Once the
instruction accepts diagnosing a report that is not known larger work (see Route remaining work),
admit it before
investigation, unless it explicitly selects one-shot work;
a discrepancy found inside an active story returns its evidence to that story's
owner instead. Its story's Goal is resolving the reported discrepancy, its
expectations are the gathered report below, and its approach is planless when
the instruction also authorizes the bounded repair, otherwise unselected. That
reference owns its checkout, refusals, continuation, and closure; an
established session decides the workspace of that admission or one-shot start.
Gather the report
Collect what the report already supplies and name the gaps:
- intended or expected behavior
- actual or observed behavior
- evidence (repro steps, tests, logs, revision, environment)
- remaining uncertainty (validity, cause, or scope)
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.
- 18d ago Changed 34d28f2baae0
- 28d ago Changed 05eca46144ec
- 1mo ago Changed 478cafb067a0
- 1mo ago Changed 275b606e07ca
- 1mo ago Changed · +13 lines 4d3e26c07eb6
- 1mo ago Changed · -6 lines 2648c765b825
- 1mo ago Changed · +13 lines bb98bed39f94
- 1mo ago Changed · +59 lines cc1a34405967
- 1mo ago First seen · 172 lines · 107 tokens per session scan A bd66e28ff6b4
dough-bug-fixing is a skill published in the GitHub repository nerds-odd-e/doughnut (50 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 3,054 once invoked, about $0.0004 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 2026-09-17.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…