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 Heapy/kortex --skill fix-issuesgit clone --depth 1 https://github.com/Heapy/kortexWrote 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/heapy/kortex/fix-issues)<a href="https://agentmods.dev/skills/heapy/kortex/fix-issues"><img src="https://agentmods.dev/badge/skills/heapy/kortex/fix-issues/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/heapy/kortex/fix-issues"><img src="https://agentmods.dev/badge/skills/heapy/kortex/fix-issues.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 | $0.00085 | $0.00795 |
| Opus 5.5 | $0.00034 | $0.00318 |
| Sonnet 5.5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
fix-issues 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Issues
Overview
Use this skill to turn an issue report or failure into a verified code change. Keep the fix narrow, evidence-driven, and aligned with the repository's existing tooling and style.
Workflow
-
Capture the issue source:
- Read the exact user request, linked issue, stack trace, failing command, PR comment, or CI log before editing.
- If the issue points to GitHub and tools are available, inspect the issue, PR, checks, or review thread before inferring requirements.
- If the referenced source is unavailable and guessing would risk the wrong fix, ask one concise blocking question.
-
Inspect the repository:
- Check
git status --shortfirst and preserve unrelated user changes. - Read the closest README, build files, package manifests, test configuration, and affected source files.
- Prefer fast searches with
rgand inspect call sites before deciding where to patch.
- Check
-
Reproduce or localize the failure:
- Run the narrowest relevant test, build, linter, script, or command first.
- Capture the exact failing assertion, exception, compiler error, or behavior.
- If the failure cannot be reproduced locally, create or update a focused test that encodes the reported behavior when practical.
-
Diagnose the root cause:
- Trace from the observed failure to the responsible code path, data shape, version, configuration, or contract mismatch.
- Prefer a fix that addresses the cause rather than hiding symptoms.
- Note any assumption that is not proven by code, tests, or logs.
-
Implement the smallest durable change:
- Follow local patterns and helper APIs instead of introducing new abstractions.
- Avoid broad refactors, formatting churn, dependency upgrades, and public API changes unless the issue requires them.
- Add or adjust tests when the bug is behavioral, regression-prone, or not already covered.
-
Verify:
- Re-run the original failing command or closest equivalent.
- Run broader relevant validation when the change touches shared behavior, build logic, dependencies, or user-facing workflows.
- If validation cannot run, state the command attempted, the blocker, and the residual risk.
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.
- 1mo ago First seen · 62 lines · 85 tokens per session scan A 640b43a8d98f
fix-issues is a skill published in the GitHub repository Heapy/kortex (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 85 tokens to every session and 795 once invoked, about $0.0003 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
technical-debt-audit
Use when the user says 'clean up my wordpress', 'what is bloating my wordpress', 'find orphaned shortcodes', or 'scan for unused plugins'. Audits orphaned shortcodes from deleted plugins, unused plugins, database bloat, unused media, and leftover data from inactive builders.
wordpress-site-dna
Use when the user says 'analyze my wordpress site', 'what is running on my site', 'site dna', or 'what plugins are on my site'. Detects every page builder, audits active versus dead-weight plugins, maps content structure, finds orphaned shortcodes, and checks performance and security posture.
diagnosing-ml-failures
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance…
debug-teacher
Use when coaching hypothesis-driven debugging that requires the learner to gather evidence and reason about root causes before applying fixes.
query-loki-project-logs
Query Grafana Loki logs that are organized by labels such as projectname or project, env, and filename, where filename distinguishes nginx, web, worker, stdout, and stderr streams. Use when Codex needs to inspect logs with logcli, discover available projects or environments, list a project's log files, narrow to a…
bug-report
Extract a structured bug report from a support ticket and create a Linear issue.