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 TweekFawkes/prompts --skill fixbugsgit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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/tweekfawkes/prompts/fixbugs)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/fixbugs"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/fixbugs.svg" alt="Measured on agentmods" 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 | $0.00153 | $0.00642 |
| Opus 5 | $0.00077 | $0.00321 |
| Sonnet 5 | $0.00031 | $0.00128 |
| Haiku 4.5 | $0.00015 | $0.00064 |
Grade A, and why
fixbugs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/fixbugs — auto-fix the bug reports filed by the auto-testing rotation
This is the standing wrapper for the /loop prompt that runs after each
auto-testing pass. Instead of pasting that long string by hand, the user runs
/fixbugs and the agent starts the same recurring fix loop.
Context
- The PRODUCER is whatever writes bug reports — a test runner, a scheduled test
rotation, or CI. It runs the test suite(s) and writes every failure as a
*.mdbug report intoz_tickets/open_bugs/(each report's "Context" section names the exact command that reproduces the failure). - This skill is the CONSUMER: it watches that directory and fixes the reports.
- Run
/fixbugsin a separate CLI session from the producer so the two sessions don't fight over the same working tree / branch.
What to do
-
Parse the argument after
/fixbugsas$INTERVAL(integer seconds). If absent or invalid, use300. Enforce a floor of 60. -
Invoke the built-in
loopskill with exactly this prompt, substituting$INTERVAL:/loop --interval $INTERVAL Scan z_tickets/open_bugs/ for *.md bug reports (skip files starting with _ or .). For each bug, oldest first: read it, reproduce the failure using the exact command in its Context, find and fix the root cause (smallest change that works), then re-run that exact command to verify it is green. On success, move the file to z_tickets/closed/ and commit on a branch. If you cannot fix or reproduce it, leave the file in place, append a short "Investigation" note, and move on. If z_tickets/open_bugs/ is empty, do nothing this iteration. -
Honor the project's guardrails while fixing: smallest change that works, never mix formatting with behavioral changes, never
--no-verifywithout approval, and keep each fix on its own branch. Production is gated — do not deploy to prod as part of a fix without explicit approval.
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.
- 8d ago First seen · 39 lines · 153 tokens per session scan A 2234a4443dae
fixbugs is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 153 tokens to every session and 642 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.